No entries match these filters. Clear filters
Dreadnode: Access enriched findings parquet exports with reviewed severity and status, audit trail, ASR, compliance tags, adversarial-ML metrics, and project rollups.
└──▷ HOW TO FIND IT
Run a white-box GCG attack against a local open-weight model as the surrogate for an AI red-teaming assessment.
📍 # supply a local open-weight model as the surrogate in the ai-red-teaming capability
# select a GCG-family white-box attack from the attack catalog when configuring the run
Score an agentic red-team run for exact tool-call landings rather than relying on a judge model.
📍 # add tool_call_attack_landed to the scorer list in your airt SDK study configuration
Pin sessions in Chat or Agents › Sessions from the menu in the Chat sidebar so pinned sessions appear at the top of the list. Not checked yet Retry dropped hosted inference streams automatically up to 3 times with exponential backoff (1 s, 2 s, 4 s) on unstable network paths. Not checked yet Improves the network-ops capability with a full toolchain now installed on local Docker sandboxes — nmap, smbclient, hashcat, john, impacket, certipy-ad, bloodyAD, and NetExec — and structured findings (hosts, users, credentials, shares, and weaknesses) viewable in Agent Output after network-ops enumeration. Not checked yet
Pin sessions in Chat or Agents › Sessions from the menu in the Chat sidebar so pinned sessions appear at the top of the list. Not checked yet Retry dropped hosted inference streams automatically up to 3 times with exponential backoff (1 s, 2 s, 4 s) on unstable network paths. Not checked yet
1 more in Everything
New navigation now live for all users
Oct 22, 2026
·
issue 123
Dreadnode adds a tool_call_attack_landed scorer for judge-free agentic red teaming and ships a third-party notices file for air-gapped Enterprise installs.
New detection Adds tool_call_attack_landed scorer for agentic red teaming — measures whether an agent emitted a specific attacker-intended tool call (name and arguments), providing a deterministic, judge-free attack success rate signal. Not checked yet Enterprise installs now include a third-party notices file downloadable from Account Settings or at https://<domain>/third-party-notices, air-gap compatible and version-matched. Not checked yet Redesigned navigation is now the default for all users on SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. and Enterprise. Not checked yet
3 details in Everything
New navigation now live for all users
Oct 22, 2026
·
issue 018
Dreadnode adds a tool_call_attack_landed scorer for judge-free agentic red teaming and ships a third-party notices file for air-gapped Enterprise installs.
New detection Adds tool_call_attack_landed scorer for agentic red teaming — measures whether an agent emitted a specific attacker-intended tool call (name and arguments), providing a deterministic, judge-free attack success rate signal. Not checked yet Enterprise installs now include a third-party notices file downloadable from Account Settings or at https://<domain>/third-party-notices, air-gap compatible and version-matched. Not checked yet Redesigned navigation is now the default for all users on SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. and Enterprise. Not checked yet
3 details in Everything
Agentic attack trace parity
Oct 15, 2026
·
issue 117
Dreadnode adds SLIP jailbreak attack, enriched findings parquet with audit/compliance columns, and session pinning in Chat and Agents.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Run a SLIP tree-search jailbreak campaign against a target model to measure attack success rate with controlled branching.
📍 In the AI red-teaming UI, select your project, choose SLIP from the attack tool list, set your target model, configure depth, branching, and judge models, then launch the campaign.
Adds SLIP self-jailbreaking attack tool to AI red-teaming, enabling tree-search-based prompt jailbreaks against a target model with configurable depth, branching, and judge models.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Enriches the findings parquet export with new columns for audit trail, ASR, compliance tags, adversarial-ML metrics, and project-level rollups, and reflects the latest operator-reviewed severity and status. Not checked yet Adds session pinning in Chat and Agents: pin sessions from the ... menu in the Chat sidebar or Agents › Sessions ; pinned sessions appear at the top of the list and are visible only to you. Not checked yet Retries hosted inference SDK streams dropped mid-connection up to 3 times with exponential backoff (1s, 2s, 4s) to reduce failures on unstable network paths. Not checked yet
Adds SLIP self-jailbreaking attack tool to AI red-teaming, enabling tree-search-based prompt jailbreaks against a target model with configurable depth, branching, and judge models.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds session pinning in Chat and Agents: pin sessions from the ... menu in the Chat sidebar or Agents › Sessions ; pinned sessions appear at the top of the list and are visible only to you. Not checked yet
2 more in Everything
Agentic attack trace parity
Oct 15, 2026
·
issue 018
Dreadnode adds SLIP jailbreak attack, enriched findings parquet with audit/compliance columns, and session pinning in Chat and Agents.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Run a SLIP tree-search jailbreak campaign against a target model to measure attack success rate with controlled branching.
📍 In the AI red-teaming UI, select your project, choose SLIP from the attack tool list, set your target model, configure depth, branching, and judge models, then launch the campaign.
Adds SLIP self-jailbreaking attack tool to AI red-teaming, enabling tree-search-based prompt jailbreaks against a target model with configurable depth, branching, and judge models.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Enriches the findings parquet export with new columns for audit trail, ASR, compliance tags, adversarial-ML metrics, and project-level rollups, and reflects the latest operator-reviewed severity and status. Not checked yet Adds session pinning in Chat and Agents: pin sessions from the ... menu in the Chat sidebar or Agents › Sessions ; pinned sessions appear at the top of the list and are visible only to you. Not checked yet Retries hosted inference SDK streams dropped mid-connection up to 3 times with exponential backoff (1s, 2s, 4s) to reduce failures on unstable network paths. Not checked yet
Adds SLIP self-jailbreaking attack tool to AI red-teaming, enabling tree-search-based prompt jailbreaks against a target model with configurable depth, branching, and judge models.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds session pinning in Chat and Agents: pin sessions from the ... menu in the Chat sidebar or Agents › Sessions ; pinned sessions appear at the top of the list and are visible only to you. Not checked yet
2 more in Everything
Dreadnode: Adds ApiClient.list_project_memories filtering by session ID so agents can trace which memories a session created, updated, or closed.
└──▷ USE IT
Apply a custom severity policy to an AIRT assessment so findings are classified against your org's own risk thresholds rather than defaults.
python
copy
assessment.severity_policy = {
'thresholds': {'critical': 0.9, 'high': 0.7, 'medium': 0.4},
'aliases': {'jailbreak': 'critical'},
'matrix': {'tool_misuse': 'high'}
}
Declare extra tool directories in a capability so uv or Go binaries installed into non-standard paths are found by agents in E2B sandboxes.
capability.yaml
copy
dependencies:
path:
- /root/.cargo/bin
- /usr/local/go/bin
Retrieve all memories that a specific session created or modified, so an agent can audit its own memory footprint for a past run.
python
copy
memories = client.list_project_memories(project_id='<project_id>', session_id='<session_id>')
for m in memories:
print(m.key, m.status)
File and folder uploads in Web Chat
Oct 8, 2026
·
issue 106
Dreadnode adds file/folder uploads in Web Chat, structured binary-analysis output, and a severity_policy parameter for AI red-teaming.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Apply a custom severity taxonomy during an AI red-team engagement so findings are classified against your org's own risk thresholds rather than defaults.
python
copy
generate_attack(severity_policy={"thresholds": {"critical": 9.0, "high": 7.0, "medium": 4.0}, "aliases": {"rce": "critical"}})
Declare extra tool directories in a capability so agents can find binaries installed outside the default PATH in E2B sandboxes.
capability.yaml
copy
dependencies:
path:
- /home/user/.cargo/bin
- /usr/local/go/bin
Trace all memories a specific session created or modified when investigating an agent run.
python
copy
ApiClient.list_project_memories(project_id="<project_id>", session_id="<session_id>")
Adds severity_policy parameter to generate_attack so you can define custom risk taxonomies — thresholds, matrices, and aliases — that the agent applies when classifying findings.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds ?tool_call=<id> linkable URL parameter and a View in transcript button in the Media tab to jump directly to the tool call that logged an artifact. Not checked yet Adds dependencies.path field in capability.yaml so capabilities can declare additional tool directories for agents running in E2B sandboxes. Not checked yet Supports filtering project memories by session ID via the API, SDK tool, and ApiClient.list_project_memories. Not checked yet Adds file, folder, and pasted-image uploads directly in Web Chat; uploads land in the runtime workspace so the agent can reference them immediately. Not checked yet
+5 more
show less
Adds a Memories tab to Sessions showing every memory the session created, updated, closed, or reopened, with links to full memory detail. Not checked yet Binary-analysis capability now emits structured findings and assets — recovered keys, vulnerability root causes, malicious capabilities, extracted payloads, and embedded endpoints — trackable through the review-and-submit workflow. Not checked yet Adds a Share action to Chat session menus so a private session can be made visible to the workspace team without leaving Chat. Not checked yet Eval sample detail page now lists worker sessions the agent started for that attempt, with links to each session in Agent Sessions. Not checked yet Web Chat capabilities picker now shows the installed version of each capability and offers an inline update when a newer version is available. Not checked yet
Adds severity_policy parameter to generate_attack so you can define custom risk taxonomies — thresholds, matrices, and aliases — that the agent applies when classifying findings.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds ?tool_call=<id> linkable URL parameter and a View in transcript button in the Media tab to jump directly to the tool call that logged an artifact. Not checked yet Adds dependencies.path field in capability.yaml so capabilities can declare additional tool directories for agents running in E2B sandboxes. Not checked yet Adds file, folder, and pasted-image uploads directly in Web Chat; uploads land in the runtime workspace so the agent can reference them immediately. Not checked yet Adds a Memories tab to Sessions showing every memory the session created, updated, closed, or reopened, with links to full memory detail. Not checked yet
+2 more
show less
Adds a Share action to Chat session menus so a private session can be made visible to the workspace team without leaving Chat. Not checked yet Eval sample detail page now lists worker sessions the agent started for that attempt, with links to each session in Agent Sessions. Not checked yet
3 more in Everything
Web Chat Interface Redesign
Oct 1, 2026
·
issue 106
Pre-launch sandbox config panel, bulk finding triage, Assessment.record_attack_result() SDK method, dataset attribution metadata in SDK push, bulk memory close/reopen, safe clickable links in agent content.
Adds Assessment.record_attack_result() SDK method so custom-target attacks (multistep tool attacks, indirect injection flows) can emit traces and materialize findings in the platform. Not checked yet Adds bulk triage on the Agent Output page — select multiple findings and set their triage status in a single action, with per-row results and a confirmation toast. Not checked yet Adds pre-launch sandbox configuration panel in the web chat session view: teams can choose capabilities, compute, secrets, and idle timeout before a sandbox starts, then inspect its runtime status, installed capabilities, health issues, and logs in a panel beside the chat. Not checked yet Adds dataset attribution metadata to SDK push: datasets now carry license, tags, language, task categories, and source provenance provenance Evidence recording where a software artifact came from and how it was built, including its source and build process. It helps a consumer check that the artifact matches a trusted build. , populating the license badge, tag filters, and Source section in the platform. Not checked yet Adds bulk close and reopen for project memories: select multiple memories on the Memories page and close or reopen them via the bulk-action bar. Not checked yet
+3 more
show less
Adds safe clickable links in agent content: links in agent messages, tool results, memories, and item notes open a confirmation dialog showing the actual destination before navigating. Not checked yet Adds organization owner management from the org detail page: owners can be added and removed directly, with a confirmation prompt when adding an unrecognized email. Not checked yet Adds a no-model-deployments informational notice on self-hosted installs with no model deployments, shown on the home page and in model-dependent CLI guides. Not checked yet
8 details in Everything
Approve or reject held tool calls in web chat
Sep 24, 2026
·
issue 085
Dreadnode adds inline tool-call approvals, eight new agentic probe families, a browsable Tool catalog, and TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. runtime log switching.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Cap an unattended red-team workflow at a specific step count to bound runaway autonomous execution.
copy
$ dn --print --max-steps 50
Adds generate_attack support for agentic-probes 2026 attacks in the ai-red-teaming agent, including transforms for argument injection, deserialization deserialization Turning stored or transmitted data back into objects a program can use. Unsafe handling of untrusted data can allow unexpected behavior or code execution. payloads, RAG RAG Retrieval-augmented generation: looking up relevant documents and adding them to the prompt before the model answers. It grounds responses in private or current data without retraining. poisoning, and covert channels, plus matching evidence-gated scorers.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds eight new agentic red-teaming probe families to the SDK: evidence-gated scorers and transforms covering tool-misuse RCE RCE Remote code execution, the ability to run attacker-chosen code on another system through a vulnerability. Its impact depends on the permissions and access that code receives. , advanced exfiltration, MINJA memory poisoning, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. line-jumping, RAG optimization attacks, and indirect prompt injection indirect prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. via the new IterInject attack loop. Not checked yet Adds a new provisionable multiagent sandbox target agentic-probes-sandbox for 2026 agentic-probe evaluation families. Not checked yet Press F5 then Tab in the TUI console to switch between local process logs and the connected runtime's server logs, with retained history up to 2,000 entries, level filtering, copy, and save. Not checked yet Adds a browsable Tool catalog in Agent Policies with searchable metadata, copyable IDs, schema fingerprints, and collapsible input schemas for every visible tool and its revision history. Not checked yet
+14 more
show less
Held tool calls now appear inline in the conversation transcript with full arguments, the policy reason, and Approve / Reject buttons, replacing the previous generic input card. Not checked yet Adds a new workbench at /beta with a new information architecture across project shell, Hub catalogs (Capabilities, Environments, Datasets, Models), Agent Outputs, and Sessions. Not checked yet Capability tools, hooks, and workers can now use standard package-relative imports instead of relying on flat module names. Not checked yet The capability detail page now shows a workflow graph of how the capability's steps connect. Not checked yet Adds an unread badge on the sidebar account button showing how many release notes have not been seen yet, clearing automatically when Release Notes is opened in Account Settings. Not checked yet Adds --max-steps N with --print for explicit autonomy budgets; unattended workflows (dn --auto, /auto, /background, --print, guard sessions, and web chat Auto/Background) now default to 100 steps. Not checked yet SDK 2.0.47 adds runtime capability health inspection for agents, and model selection for local workflow runs. Not checked yet Transcript headers now show tool policy state (active, disabled, failed, awaiting approval, or not recorded) for both live and past sessions. Not checked yet Associated workflow runs now appear inline on the Workflows page with status, duration, and run ID. Not checked yet Agent cold-start is 93% faster — median agent construction drops from ~5 s to ~0.3 s by deferring heavy imports (pandas, numpy, pyarrow, Optuna) until actually used. Not checked yet E2B sandbox pre-warming bakes server, LiteLLM, agent graph, and first-turn imports into the E2B runtime snapshot, eliminating the largest filesystem-load costs at startup. Not checked yet Trace storage uploads now run in a background pool so the first chat turn no longer waits on credential fetching or object uploads before issuing the first model request. Not checked yet SDK scope validation now runs reads concurrently with exponential backoff and an 8-second shared deadline, reducing validation latency. Not checked yet The workflow run page has a new header, node panel, transcript view, and graph direction controls. Not checked yet
Adds generate_attack support for agentic-probes 2026 attacks in the ai-red-teaming agent, including transforms for argument injection, deserialization deserialization Turning stored or transmitted data back into objects a program can use. Unsafe handling of untrusted data can allow unexpected behavior or code execution. payloads, RAG RAG Retrieval-augmented generation: looking up relevant documents and adding them to the prompt before the model answers. It grounds responses in private or current data without retraining. poisoning, and covert channels, plus matching evidence-gated scorers.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds eight new agentic red-teaming probe families to the SDK: evidence-gated scorers and transforms covering tool-misuse RCE RCE Remote code execution, the ability to run attacker-chosen code on another system through a vulnerability. Its impact depends on the permissions and access that code receives. , advanced exfiltration, MINJA memory poisoning, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. line-jumping, RAG optimization attacks, and indirect prompt injection indirect prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. via the new IterInject attack loop. Not checked yet Adds a new provisionable multiagent sandbox target agentic-probes-sandbox for 2026 agentic-probe evaluation families. Not checked yet Press F5 then Tab in the TUI console to switch between local process logs and the connected runtime's server logs, with retained history up to 2,000 entries, level filtering, copy, and save. Not checked yet Adds a browsable Tool catalog in Agent Policies with searchable metadata, copyable IDs, schema fingerprints, and collapsible input schemas for every visible tool and its revision history. Not checked yet
+5 more
show less
Adds a new workbench at /beta with a new information architecture across project shell, Hub catalogs (Capabilities, Environments, Datasets, Models), Agent Outputs, and Sessions. Not checked yet The capability detail page now shows a workflow graph of how the capability's steps connect. Not checked yet Adds an unread badge on the sidebar account button showing how many release notes have not been seen yet, clearing automatically when Release Notes is opened in Account Settings. Not checked yet SDK 2.0.47 adds runtime capability health inspection for agents, and model selection for local workflow runs. Not checked yet Transcript headers now show tool policy state (active, disabled, failed, awaiting approval, or not recorded) for both live and past sessions. Not checked yet
9 more in Everything
Workflows are now in open beta
Sep 17, 2026
·
issue 085
Dreadnode Workflows enter open beta with CLI/SDK/UI pipelines, Slack integration, and a built-in agent runtime health tool.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ HOW TO FIND IT
Connect your Dreadnode org to Slack so your team can trigger and watch agent sessions without leaving their chat workspace.
📍 In the Dreadnode UI, go to Settings → Integrations and connect your Slack workspace. Once connected, @mention the agent in any channel to stream a full session in-thread. Use the link posted in-thread to open the session in Agents → Sessions.
Adds a runtime_info built-in tool agents can call to inspect which capabilities are loaded, enabled, and healthy — including failed loads and component health — without exposing raw config or credentials.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Introduces Workflows in open beta: define, run, and inspect multi-step agent pipelines from the CLI, SDK, and a new Workflows section in the UI, with project-scoped catalog, stable graphs, inline CLI guide, and model selection at run time. Not checked yet Adds Slack integration: org owners connect a workspace via Settings → Integrations, then @mention an agent to stream a full session in-thread with stop support and a direct link back to the session in Agents → Sessions. Not checked yet Adds a memory creation panel and form on the Memories page so memories can be created directly from the UI. Not checked yet Adds organization avatars: owners can set an avatar in Settings by choosing one of five color presets, uploading a PNG, JPEG, or SVG, or falling back to the org name initial. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! The SDK now requires websockets 15.0.1 or later; environments running websockets 14.x will fail at fastmcp initialization.
Traditional ML attack targets now available across all organizations
Sep 10, 2026
·
issue 071
Dreadnode adds traditional ML attack targets, light TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. theme, /reload and /transcript chat commands, and bulk workspace membership across all orgs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Provision a public ML attack target by bare task name — no org prefix required — to kick off a membership inference campaign.
copy
$ dreadnode env provision ml-extraction-fraud-tabular
Set DREADNODE_TUI_THEME=light to switch the TUI from its default dark palette to a light theme.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds /reload slash command in chat sessions to reload the current agent without leaving the session. Not checked yet Adds /transcript command in the TUI to toggle between compact and full agent transcript views. Not checked yet Adds provision as an accepted alias for create in dreadnode env, and bare public task names (e.g. ml-extraction-fraud-tabular) now resolve without requiring an org prefix. Not checked yet Three traditional ML attack targets — fraud tabular, MNIST image , and IMDB text — are now available across all organizations, covering extraction, membership inference, evasion, and inversion attack types, provisionable by name via the SDK or TUI. Not checked yet
+8 more
show less
Adds a Release Notes section in Account Settings listing the ten most recent changelog entries with links to full docs, on both SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. and self-hosted installs. Not checked yet Capability detail view and install picker now display which credentials a capability requires before installation. Not checked yet Adds a direct link to the system status page in the Support tab of Account Settings on SaaS deployments. Not checked yet Bulk workspace member addition now lets you select and add multiple members to a workspace at once from the workspace settings page. Not checked yet Session responses now include attribution for who shared a session with the workspace and when, covering all share paths including bulk promotion and creation-time visibility. Not checked yet AIRT assessments and findings now display the workspace member who ran each assessment. Not checked yet Each session in the chat session list now displays a message count. Not checked yet Runtime cold start reduced by more than 60%, dropping time-to-ready from 18.8 s to 6.6 s. Not checked yet
Set DREADNODE_TUI_THEME=light to switch the TUI from its default dark palette to a light theme.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds /reload slash command in chat sessions to reload the current agent without leaving the session. Not checked yet Adds /transcript command in the TUI to toggle between compact and full agent transcript views. Not checked yet Three traditional ML attack targets — fraud tabular, MNIST image , and IMDB text — are now available across all organizations, covering extraction, membership inference, evasion, and inversion attack types, provisionable by name via the SDK or TUI. Not checked yet Adds a Release Notes section in Account Settings listing the ten most recent changelog entries with links to full docs, on both SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. and self-hosted installs. Not checked yet
+2 more
show less
Adds a direct link to the system status page in the Support tab of Account Settings on SaaS deployments. Not checked yet Bulk workspace member addition now lets you select and add multiple members to a workspace at once from the workspace settings page. Not checked yet
6 more in Everything
└──▷ BREAKING ON UPGRADE
! The workspace_mount runtime option is now a no-op; /home/user/workspace is ordinary sandbox-local storage. Object-storage access must go through the SDK.
Traditional ML attack targets now available across all organizations
Sep 10, 2026
·
issue 012
Dreadnode adds traditional ML attack targets, light TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. theme, /reload and /transcript chat commands, and bulk workspace membership across all orgs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Provision a public ML attack target by bare task name — no org prefix required — to kick off a membership inference campaign.
copy
$ dreadnode env provision ml-extraction-fraud-tabular
Set DREADNODE_TUI_THEME=light to switch the TUI from its default dark palette to a light theme.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds /reload slash command in chat sessions to reload the current agent without leaving the session. Not checked yet Adds /transcript command in the TUI to toggle between compact and full agent transcript views. Not checked yet Adds provision as an accepted alias for create in dreadnode env, and bare public task names (e.g. ml-extraction-fraud-tabular) now resolve without requiring an org prefix. Not checked yet Three traditional ML attack targets — fraud tabular, MNIST image , and IMDB text — are now available across all organizations, covering extraction, membership inference, evasion, and inversion attack types, provisionable by name via the SDK or TUI. Not checked yet
+8 more
show less
Adds a Release Notes section in Account Settings listing the ten most recent changelog entries with links to full docs, on both SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. and self-hosted installs. Not checked yet Capability detail view and install picker now display which credentials a capability requires before installation. Not checked yet Adds a direct link to the system status page in the Support tab of Account Settings on SaaS deployments. Not checked yet Bulk workspace member addition now lets you select and add multiple members to a workspace at once from the workspace settings page. Not checked yet Session responses now include attribution for who shared a session with the workspace and when, covering all share paths including bulk promotion and creation-time visibility. Not checked yet AIRT assessments and findings now display the workspace member who ran each assessment. Not checked yet Each session in the chat session list now displays a message count. Not checked yet Runtime cold start reduced by more than 60%, dropping time-to-ready from 18.8 s to 6.6 s. Not checked yet
Set DREADNODE_TUI_THEME=light to switch the TUI from its default dark palette to a light theme.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds /reload slash command in chat sessions to reload the current agent without leaving the session. Not checked yet Adds /transcript command in the TUI to toggle between compact and full agent transcript views. Not checked yet Three traditional ML attack targets — fraud tabular, MNIST image , and IMDB text — are now available across all organizations, covering extraction, membership inference, evasion, and inversion attack types, provisionable by name via the SDK or TUI. Not checked yet Adds a Release Notes section in Account Settings listing the ten most recent changelog entries with links to full docs, on both SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. and self-hosted installs. Not checked yet
+2 more
show less
Adds a direct link to the system status page in the Support tab of Account Settings on SaaS deployments. Not checked yet Bulk workspace member addition now lets you select and add multiple members to a workspace at once from the workspace settings page. Not checked yet
6 more in Everything
└──▷ BREAKING ON UPGRADE
! The workspace_mount runtime option is now a no-op; /home/user/workspace is ordinary sandbox-local storage. Object-storage access must go through the SDK.
Offline SDK and CLI install for air-gapped deployments
Sep 3, 2026
·
issue 071
Dreadnode adds offline SDK/CLI bundles, a Global Tool Registry API, multi-agent red-teaming tasks, and Cloudflare Workers OAST OAST Out-of-band Application Security Testing: a technique for detecting vulnerabilities by having a target system make DNS or HTTP callbacks to an attacker-controlled server, revealing flaws that produce no visible in-band response. support for air-gapped deployments.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Enumerate all registered tools in your organization to audit capability surface before a red-team engagement.
copy
$ curl -s -H 'Authorization: Bearer <token>' https://<your-instance>/api/v1/tools | jq '.[].id'
Inspect the cold-start timing breakdown on a slow runtime to attribute whether delay is provider provisioning or package install.
copy
$ dn runtime start && curl -s -H 'Authorization: Bearer <token>' https://<your-instance>/runtimes/<id> | jq '.timing'
Inject an internal CA into the Node frontend on a self-hosted air-gapped deployment so TLS to an on-prem model proxy is trusted.
values.yaml
copy
caBundle: |
-----BEGIN CERTIFICATE-----
<your-internal-CA-cert>
-----END CERTIFICATE-----
Adds GET /api/v1/tools and GET /api/v1/tools/{tool_id} endpoints to query the new Global Tool Registry, giving published capability Python tools and command wrappers stable, organization-scoped identities with immutable revision history.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds caBundle config key for self-hosted deployments to inject a custom CA bundle into the Node frontend, completing CA trust support across all workloads (API, LiteLLM, and frontend). Not checked yet Surfaces full cold-start timing breakdown (total, platform overhead, provider provisioning, boot, installs, slowest step) via dn runtime start and GET /runtimes/{id}. Not checked yet Serves the SDK and CLI as self-contained offline bundles from self-hosted deployments, enabling install without reaching PyPI or any external host. Not checked yet Serves documentation at /docs inside every deployment for air-gapped and on-prem operators. Not checked yet
+13 more
show less
Adds organization-owner-configurable lifetime credit cap per non-owner member, visible to capped members under Settings → Billing. Not checked yet Adds bulk share-with-workspace action for multiple agent sessions via the floating action bar. Not checked yet Adds Cloudflare Workers support via wrangler to the web-security capability for deploying programmable OAST endpoints, enabling blind XSS XSS Cross-site scripting, an attack that runs malicious script in another user's browser through a trusted site. It can steal data or perform actions using the user's session. payload hosting, callback logging, and SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. chain redirection. Not checked yet Adds signup IP allow-list mode letting admins restrict new account creation to explicitly approved IPv4/IPv6 IPv6 The current version of the Internet Protocol, standardized by the IETF, using 128-bit addresses to replace the exhausted IPv4 space. Cyber tools target it because modern networks run dual-stack or IPv6-only. CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. ranges with deny rules taking precedence. Not checked yet Adds 12 multi-agent AI red-teaming tasks covering access-control bypass, indirect injection, memory poisoning, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. poisoning, reasoning hijack, supply-chain, data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. , DevOps RCE RCE Remote code execution, the ability to run attacker-chosen code on another system through a vulnerability. Its impact depends on the permissions and access that code receives. , and sector-specific meshes to the task catalog under the airt-generative-ai set. Not checked yet Adds an indirect prompt injection indirect prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. web task where agents must detect injections hidden via HTML comments, hidden CSS, off-screen ARIA, white-on-white text, and Unicode tags across a public web page. Not checked yet Adds an agentic CI/CD secret-exfiltration multiagent task simulating hidden instructions in untrusted repo content that cause a CI assistant to leak its deploy secret. Not checked yet Adds a multi-step tool attack sandbox task featuring an over-permissioned agent with file, database, email, and HTTP tools where success requires chaining a sensitive data source to an external exfiltration sink. Not checked yet Adds two honeytoken tools to the ai-red-teaming capability: mint canary tokens (exfil or RCE variants) and check whether a target agent leaked them across an output boundary. Not checked yet Adds algorithmic multi-step tool-attack search to the AI red-teaming agent for finding replay-stable read-then-exfiltrate causal paths across HTTP agent tool call chains. Not checked yet Adds a turnkey OWASP OWASP A nonprofit foundation that publishes open standards, guides, and ranked vulnerability lists—most famously the OWASP Top 10—giving cyber tools a vendor-neutral benchmark to test or report against. -ASI agentic attack suite runner, argument-aware tool-evidence scoring, and a honeytoken harness for black-box exfil and RCE detection to the SDK. Not checked yet Adds environment-agnostic attack-success detection to the airt SDK using canary exfiltration, OAST beacons, dataflow taint, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge scoring, and optional customer-defined success policies to produce confidence-rated verdicts. Not checked yet Adds SDK transforms and scorers covering search-query and trusted-domain image exfiltration channels plus dedicated browser-attack scorers for visual injection, ClickFix execution, navigation hijacking, and domain-validation bypass. Not checked yet
Adds GET /api/v1/tools and GET /api/v1/tools/{tool_id} endpoints to query the new Global Tool Registry, giving published capability Python tools and command wrappers stable, organization-scoped identities with immutable revision history.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Serves the SDK and CLI as self-contained offline bundles from self-hosted deployments, enabling install without reaching PyPI or any external host. Not checked yet Serves documentation at /docs inside every deployment for air-gapped and on-prem operators. Not checked yet Adds organization-owner-configurable lifetime credit cap per non-owner member, visible to capped members under Settings → Billing. Not checked yet Adds bulk share-with-workspace action for multiple agent sessions via the floating action bar. Not checked yet
+11 more
show less
Adds Cloudflare Workers support via wrangler to the web-security capability for deploying programmable OAST endpoints, enabling blind XSS XSS Cross-site scripting, an attack that runs malicious script in another user's browser through a trusted site. It can steal data or perform actions using the user's session. payload hosting, callback logging, and SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. chain redirection. Not checked yet Adds signup IP allow-list mode letting admins restrict new account creation to explicitly approved IPv4/IPv6 IPv6 The current version of the Internet Protocol, standardized by the IETF, using 128-bit addresses to replace the exhausted IPv4 space. Cyber tools target it because modern networks run dual-stack or IPv6-only. CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. ranges with deny rules taking precedence. Not checked yet Adds 12 multi-agent AI red-teaming tasks covering access-control bypass, indirect injection, memory poisoning, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. poisoning, reasoning hijack, supply-chain, data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. , DevOps RCE RCE Remote code execution, the ability to run attacker-chosen code on another system through a vulnerability. Its impact depends on the permissions and access that code receives. , and sector-specific meshes to the task catalog under the airt-generative-ai set. Not checked yet Adds an indirect prompt injection indirect prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. web task where agents must detect injections hidden via HTML comments, hidden CSS, off-screen ARIA, white-on-white text, and Unicode tags across a public web page. Not checked yet Adds an agentic CI/CD secret-exfiltration multiagent task simulating hidden instructions in untrusted repo content that cause a CI assistant to leak its deploy secret. Not checked yet Adds a multi-step tool attack sandbox task featuring an over-permissioned agent with file, database, email, and HTTP tools where success requires chaining a sensitive data source to an external exfiltration sink. Not checked yet Adds two honeytoken tools to the ai-red-teaming capability: mint canary tokens (exfil or RCE variants) and check whether a target agent leaked them across an output boundary. Not checked yet Adds algorithmic multi-step tool-attack search to the AI red-teaming agent for finding replay-stable read-then-exfiltrate causal paths across HTTP agent tool call chains. Not checked yet Adds a turnkey OWASP OWASP A nonprofit foundation that publishes open standards, guides, and ranked vulnerability lists—most famously the OWASP Top 10—giving cyber tools a vendor-neutral benchmark to test or report against. -ASI agentic attack suite runner, argument-aware tool-evidence scoring, and a honeytoken harness for black-box exfil and RCE detection to the SDK. Not checked yet Adds environment-agnostic attack-success detection to the airt SDK using canary exfiltration, OAST beacons, dataflow taint, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge scoring, and optional customer-defined success policies to produce confidence-rated verdicts. Not checked yet Adds SDK transforms and scorers covering search-query and trusted-domain image exfiltration channels plus dedicated browser-attack scorers for visual injection, ClickFix execution, navigation hijacking, and domain-validation bypass. Not checked yet
2 more in Everything
Offline SDK and CLI install for air-gapped deployments
Sep 3, 2026
·
issue 012
Dreadnode adds offline SDK/CLI bundles, a Global Tool Registry API, multi-agent red-teaming tasks, and Cloudflare Workers OAST OAST Out-of-band Application Security Testing: a technique for detecting vulnerabilities by having a target system make DNS or HTTP callbacks to an attacker-controlled server, revealing flaws that produce no visible in-band response. support for air-gapped deployments.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Enumerate all registered tools in your organization to audit capability surface before a red-team engagement.
copy
$ curl -s -H 'Authorization: Bearer <token>' https://<your-instance>/api/v1/tools | jq '.[].id'
Inspect the cold-start timing breakdown on a slow runtime to attribute whether delay is provider provisioning or package install.
copy
$ dn runtime start && curl -s -H 'Authorization: Bearer <token>' https://<your-instance>/runtimes/<id> | jq '.timing'
Inject an internal CA into the Node frontend on a self-hosted air-gapped deployment so TLS to an on-prem model proxy is trusted.
values.yaml
copy
caBundle: |
-----BEGIN CERTIFICATE-----
<your-internal-CA-cert>
-----END CERTIFICATE-----
Adds GET /api/v1/tools and GET /api/v1/tools/{tool_id} endpoints to query the new Global Tool Registry, giving published capability Python tools and command wrappers stable, organization-scoped identities with immutable revision history.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds caBundle config key for self-hosted deployments to inject a custom CA bundle into the Node frontend, completing CA trust support across all workloads (API, LiteLLM, and frontend). Not checked yet Surfaces full cold-start timing breakdown (total, platform overhead, provider provisioning, boot, installs, slowest step) via dn runtime start and GET /runtimes/{id}. Not checked yet Serves the SDK and CLI as self-contained offline bundles from self-hosted deployments, enabling install without reaching PyPI or any external host. Not checked yet Serves documentation at /docs inside every deployment for air-gapped and on-prem operators. Not checked yet
+13 more
show less
Adds organization-owner-configurable lifetime credit cap per non-owner member, visible to capped members under Settings → Billing. Not checked yet Adds bulk share-with-workspace action for multiple agent sessions via the floating action bar. Not checked yet Adds Cloudflare Workers support via wrangler to the web-security capability for deploying programmable OAST endpoints, enabling blind XSS XSS Cross-site scripting, an attack that runs malicious script in another user's browser through a trusted site. It can steal data or perform actions using the user's session. payload hosting, callback logging, and SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. chain redirection. Not checked yet Adds signup IP allow-list mode letting admins restrict new account creation to explicitly approved IPv4/IPv6 IPv6 The current version of the Internet Protocol, standardized by the IETF, using 128-bit addresses to replace the exhausted IPv4 space. Cyber tools target it because modern networks run dual-stack or IPv6-only. CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. ranges with deny rules taking precedence. Not checked yet Adds 12 multi-agent AI red-teaming tasks covering access-control bypass, indirect injection, memory poisoning, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. poisoning, reasoning hijack, supply-chain, data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. , DevOps RCE RCE Remote code execution, the ability to run attacker-chosen code on another system through a vulnerability. Its impact depends on the permissions and access that code receives. , and sector-specific meshes to the task catalog under the airt-generative-ai set. Not checked yet Adds an indirect prompt injection indirect prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. web task where agents must detect injections hidden via HTML comments, hidden CSS, off-screen ARIA, white-on-white text, and Unicode tags across a public web page. Not checked yet Adds an agentic CI/CD secret-exfiltration multiagent task simulating hidden instructions in untrusted repo content that cause a CI assistant to leak its deploy secret. Not checked yet Adds a multi-step tool attack sandbox task featuring an over-permissioned agent with file, database, email, and HTTP tools where success requires chaining a sensitive data source to an external exfiltration sink. Not checked yet Adds two honeytoken tools to the ai-red-teaming capability: mint canary tokens (exfil or RCE variants) and check whether a target agent leaked them across an output boundary. Not checked yet Adds algorithmic multi-step tool-attack search to the AI red-teaming agent for finding replay-stable read-then-exfiltrate causal paths across HTTP agent tool call chains. Not checked yet Adds a turnkey OWASP OWASP A nonprofit foundation that publishes open standards, guides, and ranked vulnerability lists—most famously the OWASP Top 10—giving cyber tools a vendor-neutral benchmark to test or report against. -ASI agentic attack suite runner, argument-aware tool-evidence scoring, and a honeytoken harness for black-box exfil and RCE detection to the SDK. Not checked yet Adds environment-agnostic attack-success detection to the airt SDK using canary exfiltration, OAST beacons, dataflow taint, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge scoring, and optional customer-defined success policies to produce confidence-rated verdicts. Not checked yet Adds SDK transforms and scorers covering search-query and trusted-domain image exfiltration channels plus dedicated browser-attack scorers for visual injection, ClickFix execution, navigation hijacking, and domain-validation bypass. Not checked yet
Adds GET /api/v1/tools and GET /api/v1/tools/{tool_id} endpoints to query the new Global Tool Registry, giving published capability Python tools and command wrappers stable, organization-scoped identities with immutable revision history.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Serves the SDK and CLI as self-contained offline bundles from self-hosted deployments, enabling install without reaching PyPI or any external host. Not checked yet Serves documentation at /docs inside every deployment for air-gapped and on-prem operators. Not checked yet Adds organization-owner-configurable lifetime credit cap per non-owner member, visible to capped members under Settings → Billing. Not checked yet Adds bulk share-with-workspace action for multiple agent sessions via the floating action bar. Not checked yet
+11 more
show less
Adds Cloudflare Workers support via wrangler to the web-security capability for deploying programmable OAST endpoints, enabling blind XSS XSS Cross-site scripting, an attack that runs malicious script in another user's browser through a trusted site. It can steal data or perform actions using the user's session. payload hosting, callback logging, and SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. chain redirection. Not checked yet Adds signup IP allow-list mode letting admins restrict new account creation to explicitly approved IPv4/IPv6 IPv6 The current version of the Internet Protocol, standardized by the IETF, using 128-bit addresses to replace the exhausted IPv4 space. Cyber tools target it because modern networks run dual-stack or IPv6-only. CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. ranges with deny rules taking precedence. Not checked yet Adds 12 multi-agent AI red-teaming tasks covering access-control bypass, indirect injection, memory poisoning, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. poisoning, reasoning hijack, supply-chain, data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. , DevOps RCE RCE Remote code execution, the ability to run attacker-chosen code on another system through a vulnerability. Its impact depends on the permissions and access that code receives. , and sector-specific meshes to the task catalog under the airt-generative-ai set. Not checked yet Adds an indirect prompt injection indirect prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. web task where agents must detect injections hidden via HTML comments, hidden CSS, off-screen ARIA, white-on-white text, and Unicode tags across a public web page. Not checked yet Adds an agentic CI/CD secret-exfiltration multiagent task simulating hidden instructions in untrusted repo content that cause a CI assistant to leak its deploy secret. Not checked yet Adds a multi-step tool attack sandbox task featuring an over-permissioned agent with file, database, email, and HTTP tools where success requires chaining a sensitive data source to an external exfiltration sink. Not checked yet Adds two honeytoken tools to the ai-red-teaming capability: mint canary tokens (exfil or RCE variants) and check whether a target agent leaked them across an output boundary. Not checked yet Adds algorithmic multi-step tool-attack search to the AI red-teaming agent for finding replay-stable read-then-exfiltrate causal paths across HTTP agent tool call chains. Not checked yet Adds a turnkey OWASP OWASP A nonprofit foundation that publishes open standards, guides, and ranked vulnerability lists—most famously the OWASP Top 10—giving cyber tools a vendor-neutral benchmark to test or report against. -ASI agentic attack suite runner, argument-aware tool-evidence scoring, and a honeytoken harness for black-box exfil and RCE detection to the SDK. Not checked yet Adds environment-agnostic attack-success detection to the airt SDK using canary exfiltration, OAST beacons, dataflow taint, LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge scoring, and optional customer-defined success policies to produce confidence-rated verdicts. Not checked yet Adds SDK transforms and scorers covering search-query and trusted-domain image exfiltration channels plus dedicated browser-attack scorers for visual injection, ClickFix execution, navigation hijacking, and domain-validation bypass. Not checked yet
2 more in Everything
Web Chat open to all users
Aug 27, 2026
·
issue 071
Dreadnode opens Web Chat to all users, adds air-gap deployment, HTTP desync HTTP desync An attack technique that exploits disagreements between a front-end proxy and a back-end server about where one HTTP request ends and the next begins, letting an attacker poison the request queue and hijack other users' traffic. detection, IP rotation, geo-DNS geo-DNS A DNS service that returns different answers based on the requester's geographic location, letting cyber tools route users to the nearest or most appropriate server automatically. , and LSB steganography LSB steganography A data-hiding technique that encodes secret bytes into the least-significant bits of image, audio, or video samples, making changes imperceptible to human senses while preserving a covert channel inside ordinary files. in web-security.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Check your current session context at a glance in the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. without leaving the chat interface.
List only the runtimes you own to avoid acting on a colleague's shared runtime in a multi-user workspace.
copy
$ dn runtime ls --mine
Prevent the Replicated SDK pod from phoning home during a Helm-based air-gap install in a disconnected environment.
copy
$ helm upgrade --install dreadnode ./dreadnode-chart --set replicated.isAirgap=true
Adds replicated.isAirgap=true Helm CLI setting to prevent the Replicated SDK pod from attempting outbound connections to replicated.app in air-gapped installs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds --mine flag to dn runtime ls to filter runtimes to only those you own; also marks runtimes you do not own in the default listing. Not checked yet Adds /status slash command to the TUI, displaying current session, model, user, org, workspace, and project at a glance. Not checked yet Adds IP rotation tool to the web-security capability, deploying Cloudflare Worker proxies on demand for round-robin egress through rotating IPs during engagements. Not checked yet Adds HTTP desync and request-smuggling detection to the web-security capability, covering 11 smuggling families with fingerprinting, payload construction, cache-poisoning detection, and victim-response classification. Not checked yet
+10 more
show less
Adds geo-distributed DNS resolution to the web-security capability, resolving target hostnames through open resolvers in multiple countries (via Shodan or Censys) to detect geo-fenced infrastructure, GSLB routing, and region-locked DNS responses. Not checked yet Adds LSB steganography support for PNG images to the web-security capability, enabling payload-smuggling tests and upload pipeline inspection via the built-in Python tool. Not checked yet Adds air-gap deployment mode that vendors all front-end resources locally, hides the analytics notebook, serves model pricing from a bundled catalog, and pre-bakes capability dependencies into the runtime image so sandbox boot requires no network access. Not checked yet Adds support to self-hosted Helm charts for non-root container execution and custom CA bundle mounts for outbound TLS trust in private-CA environments. Not checked yet Adds bulk archive and unarchive for agent sessions from the Sessions tab, with context-aware actions for active, archived, or mixed selections. Not checked yet Surfaces failed capability preflight checks (e.g. missing dnsx, katana) as explicit warnings in the agent system prompt and operator logs instead of silently proceeding. Not checked yet Expands postMessage handler detection in the web-security capability's DOM DOM The browser's in-memory tree representation of a web page's structure, standardized by the W3C, giving cyber tools a programmable interface to read or manipulate page content at runtime. analysis to cover window.onmessage, MessagePort/MessageChannel, and monitoring-shim wrappers, plus additional origin-validation bypass patterns including unescaped-dot and missing-anchor regex bugs. Not checked yet Adds guard invocation highlighting in session transcripts, showing policy decisions inline within the conversation view. Not checked yet Adds pagination and full-text search by title, model, agent, and label to the chat session list, removing the previous 100-session cap. Not checked yet Adds six new documentation pages covering Web Chat: overview, quickstart, sessions, runtimes, agents and models, and slash commands. Not checked yet
Adds replicated.isAirgap=true Helm CLI setting to prevent the Replicated SDK pod from attempting outbound connections to replicated.app in air-gapped installs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds /status slash command to the TUI, displaying current session, model, user, org, workspace, and project at a glance. Not checked yet Adds IP rotation tool to the web-security capability, deploying Cloudflare Worker proxies on demand for round-robin egress through rotating IPs during engagements. Not checked yet Adds HTTP desync and request-smuggling detection to the web-security capability, covering 11 smuggling families with fingerprinting, payload construction, cache-poisoning detection, and victim-response classification. Not checked yet Adds geo-distributed DNS resolution to the web-security capability, resolving target hostnames through open resolvers in multiple countries (via Shodan or Censys) to detect geo-fenced infrastructure, GSLB routing, and region-locked DNS responses. Not checked yet
+5 more
show less
Adds LSB steganography support for PNG images to the web-security capability, enabling payload-smuggling tests and upload pipeline inspection via the built-in Python tool. Not checked yet Adds air-gap deployment mode that vendors all front-end resources locally, hides the analytics notebook, serves model pricing from a bundled catalog, and pre-bakes capability dependencies into the runtime image so sandbox boot requires no network access. Not checked yet Adds bulk archive and unarchive for agent sessions from the Sessions tab, with context-aware actions for active, archived, or mixed selections. Not checked yet Adds guard invocation highlighting in session transcripts, showing policy decisions inline within the conversation view. Not checked yet Adds six new documentation pages covering Web Chat: overview, quickstart, sessions, runtimes, agents and models, and slash commands. Not checked yet
5 more in Everything
Web Chat open to all users
Aug 27, 2026
·
issue 012
Dreadnode opens Web Chat to all users, adds air-gap deployment, HTTP desync HTTP desync An attack technique that exploits disagreements between a front-end proxy and a back-end server about where one HTTP request ends and the next begins, letting an attacker poison the request queue and hijack other users' traffic. detection, IP rotation, geo-DNS geo-DNS A DNS service that returns different answers based on the requester's geographic location, letting cyber tools route users to the nearest or most appropriate server automatically. , and LSB steganography LSB steganography A data-hiding technique that encodes secret bytes into the least-significant bits of image, audio, or video samples, making changes imperceptible to human senses while preserving a covert channel inside ordinary files. in web-security.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Check your current session context at a glance in the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. without leaving the chat interface.
List only the runtimes you own to avoid acting on a colleague's shared runtime in a multi-user workspace.
copy
$ dn runtime ls --mine
Prevent the Replicated SDK pod from phoning home during a Helm-based air-gap install in a disconnected environment.
copy
$ helm upgrade --install dreadnode ./dreadnode-chart --set replicated.isAirgap=true
Adds replicated.isAirgap=true Helm CLI setting to prevent the Replicated SDK pod from attempting outbound connections to replicated.app in air-gapped installs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds --mine flag to dn runtime ls to filter runtimes to only those you own; also marks runtimes you do not own in the default listing. Not checked yet Adds /status slash command to the TUI, displaying current session, model, user, org, workspace, and project at a glance. Not checked yet Adds IP rotation tool to the web-security capability, deploying Cloudflare Worker proxies on demand for round-robin egress through rotating IPs during engagements. Not checked yet Adds HTTP desync and request-smuggling detection to the web-security capability, covering 11 smuggling families with fingerprinting, payload construction, cache-poisoning detection, and victim-response classification. Not checked yet
+10 more
show less
Adds geo-distributed DNS resolution to the web-security capability, resolving target hostnames through open resolvers in multiple countries (via Shodan or Censys) to detect geo-fenced infrastructure, GSLB routing, and region-locked DNS responses. Not checked yet Adds LSB steganography support for PNG images to the web-security capability, enabling payload-smuggling tests and upload pipeline inspection via the built-in Python tool. Not checked yet Adds air-gap deployment mode that vendors all front-end resources locally, hides the analytics notebook, serves model pricing from a bundled catalog, and pre-bakes capability dependencies into the runtime image so sandbox boot requires no network access. Not checked yet Adds support to self-hosted Helm charts for non-root container execution and custom CA bundle mounts for outbound TLS trust in private-CA environments. Not checked yet Adds bulk archive and unarchive for agent sessions from the Sessions tab, with context-aware actions for active, archived, or mixed selections. Not checked yet Surfaces failed capability preflight checks (e.g. missing dnsx, katana) as explicit warnings in the agent system prompt and operator logs instead of silently proceeding. Not checked yet Expands postMessage handler detection in the web-security capability's DOM DOM The browser's in-memory tree representation of a web page's structure, standardized by the W3C, giving cyber tools a programmable interface to read or manipulate page content at runtime. analysis to cover window.onmessage, MessagePort/MessageChannel, and monitoring-shim wrappers, plus additional origin-validation bypass patterns including unescaped-dot and missing-anchor regex bugs. Not checked yet Adds guard invocation highlighting in session transcripts, showing policy decisions inline within the conversation view. Not checked yet Adds pagination and full-text search by title, model, agent, and label to the chat session list, removing the previous 100-session cap. Not checked yet Adds six new documentation pages covering Web Chat: overview, quickstart, sessions, runtimes, agents and models, and slash commands. Not checked yet
Adds replicated.isAirgap=true Helm CLI setting to prevent the Replicated SDK pod from attempting outbound connections to replicated.app in air-gapped installs.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds /status slash command to the TUI, displaying current session, model, user, org, workspace, and project at a glance. Not checked yet Adds IP rotation tool to the web-security capability, deploying Cloudflare Worker proxies on demand for round-robin egress through rotating IPs during engagements. Not checked yet Adds HTTP desync and request-smuggling detection to the web-security capability, covering 11 smuggling families with fingerprinting, payload construction, cache-poisoning detection, and victim-response classification. Not checked yet Adds geo-distributed DNS resolution to the web-security capability, resolving target hostnames through open resolvers in multiple countries (via Shodan or Censys) to detect geo-fenced infrastructure, GSLB routing, and region-locked DNS responses. Not checked yet
+5 more
show less
Adds LSB steganography support for PNG images to the web-security capability, enabling payload-smuggling tests and upload pipeline inspection via the built-in Python tool. Not checked yet Adds air-gap deployment mode that vendors all front-end resources locally, hides the analytics notebook, serves model pricing from a bundled catalog, and pre-bakes capability dependencies into the runtime image so sandbox boot requires no network access. Not checked yet Adds bulk archive and unarchive for agent sessions from the Sessions tab, with context-aware actions for active, archived, or mixed selections. Not checked yet Adds guard invocation highlighting in session transcripts, showing policy decisions inline within the conversation view. Not checked yet Adds six new documentation pages covering Web Chat: overview, quickstart, sessions, runtimes, agents and models, and slash commands. Not checked yet
5 more in Everything
Kubernetes Gateway API support for on-prem installs
Aug 20, 2026
·
issue 056
Dreadnode adds Kubernetes Gateway API routing, a Caido TypeScript SDK skill, new web-security attacks, bulk session freeze, and media previews.
└──▷ TRY IT
Use a paid webhook.site account in the callback tool to avoid anonymous rate limits during web-security agent runs.
copy
$ export WEBHOOK_SITE_API_KEY=your-api-key-here
Adds WEBHOOK_SITE_API_KEY environment variable to the web-security callback tool, enabling a paid webhook.site account to bypass rate limits while preserving anonymous and interactsh fallback. Not checked yet Supports Kubernetes Gateway API (HTTPRoute ) routing for on-prem deployments, enabling installations on Istio, Envoy Gateway, and Cilium stacks instead of relying on Ingress. Not checked yet Adds a caido-mode skill in the web-security capability, exposing the full Caido TypeScript SDK — including Match & Replace rules, replay sessions, HTTPQL history search, findings management, and curl-through-Caido testing — from within an agent. Not checked yet Adds three new web-security attack skills: SQL-injection-to-RCE RCE Remote code execution, the ability to run attacker-chosen code on another system through a vulnerability. Its impact depends on the permissions and access that code receives. escalation, MathJax MathJax An open-source JavaScript library that renders LaTeX and MathML math notation in web browsers, giving cyber tools a reliable way to display formatted equations without server-side processing. /KaTeX macro injection, and an ORB/XS-Leak browser side-channel via service-worker fetch proxy. Not checked yet Enables bulk freeze of multiple agent sessions from the Agent Sessions tab, with a confirmation dialog before sessions are affected. Not checked yet
+3 more
show less
Embeds image, audio, and video previews directly in the output panel alongside existing field data. Not checked yet Adds ATIF dataset and replay downloads in the Worlds UI: download the full ATIF dataset from Worlds → Jobs, or export the normalized replay payload as JSON from the Trajectories page. Not checked yet Adds typed DELETE-{count} challenge confirmation for bulk and single-row session deletes, guarding against accidental permanent deletion. Not checked yet
8 details in Everything
Versioned item type registry for structured agent output
seen Aug 19, 2026
·
issue 050
Dreadnode adds a versioned item type registry, ScopeGuard in remote/headless sessions, Caido MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server, and a response-queue-poisoning skill.
Adds a versioned item type registry backing structured agent output: platform admins can define, publish, and manage structured output structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. contracts (findings, assets, and custom types) via Operations → Objects , with capabilities binding to approved registry versions and all item writes validated against the canonical schema. Not checked yet Adds ScopeGuard policy support in remote and headless sessions via the SDK Experimental ; the session UI renders tool-call policy decisions when ScopeGuard metadata is present — opt-in, with no workspace setting or picker entry yet. Not checked yet Adds the full Caido MCP server (66 tools, 6 resources) as a second MCP server in the web-security capability, alongside the existing Python wrapper, both targeting the same Caido instance. Not checked yet Adds a response-queue-poisoning skill to the web-security capability, covering CRLF-powered desync attacks including response queue poisoning and request tunnelling via HTTP header injection. Not checked yet Adds a spinner (or plain status line in non-interactive output) to dn evaluation create while the evaluation is being submitted. Not checked yet
+6 more
show less
Adds bulk session delete: multiple agent sessions can now be selected and deleted together, with deleted sessions disappearing from the list immediately without a page refresh. Not checked yet Adds a new sandbox isolation reference page covering Firecracker compute isolation, application authentication, public sandbox routing, outbound internet access, credential scope, and shared responsibility. Not checked yet Adds a --include-public flag documentation clarification for Hub browse pages (Datasets , Models , Capabilities , Environments ), distinguishing CLI --include-public behavior from the Public scope tab. Not checked yet Redesigns the capabilities UI with improved navigation, richer detail views for agents, skills, and MCP servers, and a new file browser for capability contents. Not checked yet Makes the model slug visible by default in session metadata so the exact model used is identifiable without extra clicks. Not checked yet Reader-role orgs are now visibly marked and disabled in the New Workspace dialog to prevent 403 errors on form submission. Not checked yet
11 details in Everything
Versioned item type registry for structured agent output
Aug 13, 2026
· release notes
New versioned item type registry for structured agent output and ScopeGuard in remote sessions.
Adds a versioned item type registry for agent output, allowing admins to define schemas via Operations → Objects Not checked yet Enables ScopeGuard policy usage in remote and headless sessions via the SDK Not checked yet Includes full Caido MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server (66 tools) in web-security capability alongside existing Python wrapper Not checked yet Adds bulk session deletion with immediate list update Not checked yet Adds response-queue-poisoning skill covering CRLF-powered desync attacks Not checked yet
+1 more
show less
Displays model slug by default in session metadata Not checked yet
6 details in Everything
Dreadnode adds explicit hidden model visibility control, clickable stat-card filters for Agent Outputs, and media gallery color coding.
└──▷ HOW TO FIND IT
Filter Agent Outputs to show only items requiring review.
📍 Click the Needs review stat card on the Agent Outputs page
Adds hidden attribute to models; operators set this explicitly to hide models from pickers, member grants, and SDK keys Not checked yet Agent Outputs page stat cards (Needs review , Critical + High ) are now clickable filter toggles Not checked yet Session Media gallery adds color coding by media kind and improved layout Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Model visibility no longer uses name-prefix convention; operators must use the hidden attribute to hide models
Agent memory, triage, and session monitoring overhaul
seen Aug 4, 2026
·
issue 035
Dreadnode adds agent memory UI, five data-integration connectors, air-gapped hub sync commands, AST AST An abstract syntax tree, a structured representation of parsed code. Tools inspect or transform this tree to understand expressions and statements rather than just matching text. -based JS/TS analysis, and in-place finding triage.
└──▷ TRY IT
File a bug report from the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. immediately after a crash without losing session logs.
Adds dn capability sync and dn task sync CLI commands to pull hub content from SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. (or another on-prem) into a local directory and push it to a self-hosted instance, enabling air-gapped on-prem loading. Not checked yet Adds /report-bug command (or r in console) to the TUI, assembling a privacy-reviewed diagnostic bundle and submitting it without losing logs after a crash. Not checked yet Adds the llm-wiki capability (compiles source material into linked wiki pages) and analysis-ledger capability (maintains a resumable code-analysis frontier with evidence-bearing claims). Not checked yet Adds five data-integration connectors — Atlassian, Azure DevOps, GitHub, GitLab, and Linear — as platform capabilities. Not checked yet Adds AST-based JS/TS static analysis via ast-grep in the web-security runtime, removing the need for semgrep, CodeQL, or a jxscout license. Not checked yet
+9 more
show less
Adds an Inactive filter to Agent Sessions to isolate sessions idle past 15 minutes but not yet archived. Not checked yet New Memories page under Agents lets operators view, inspect, and manage project memory entries, including version history and diffs. Not checked yet Enables finding triage (status and notes) directly from a finding's detail panel in Agent Output. Not checked yet Session monitoring redesigned: adds a Last Msg relative-activity column, highlights sessions active in the last 15 minutes, and adds forward/backward transcript pagination with tailing mode. Not checked yet Stat cards for Needs review and Critical + High on the Agent Outputs page are now clickable filter toggles; the items grid gains a sortable Updated column. Not checked yet Sessions group-by control (None / Workflow / Capability / Agent / Source) is now available to all orgs, with workflow runs collapsed by default. Not checked yet Models and Datasets Hub browse pages add a table view alongside cards, with a unified toolbar offering separate sort and filter controls across all four Hub browse pages. Not checked yet New workspace dialog includes an organization picker to create a workspace in any org without switching context. Not checked yet Agent Output items from failed report_item POSTs are automatically recovered from span backups when a session is frozen. Not checked yet
14 details in Everything
Traditional-ML red teaming suite — evasion, extraction, membership inference, and model inversion in one platform
seen Aug 4, 2026
·
issue 035
Dreadnode adds 20+ traditional-ML attacks, dn airt run-classifier CLI, multi-agent ATLAS campaigns, and eval agent selection to its red teaming platform.
└──▷ TRY IT
Pin a specific agent to an evaluation run so results are reproducible and the run report identifies which agent executed.
copy
$ dn evaluation create --agent <name>
Increase the number of project memories available at session start beyond the default of 20 to give agents broader context on large engagements.
copy
$ dn ... --project-memory-preload-limit 100
New dn airt run-classifier CLI command runs classic-ML attacks — evasion, extraction, membership inference, and model inversion — directly against a predict endpoint without SDK code. Not checked yet New dn evaluation create --agent <name> flag specifies which agent runs in an evaluation; eval output reports which agent actually ran. Not checked yet New --project-memory-preload-limit flag sets the number of memories preloaded at session start (range: 1–200), replacing a hardcoded default of 20. Not checked yet Adds four traditional-ML attack families (evasion, extraction, membership inference, model inversion) to AIRT, covering 20+ named attacks — including equation-solving, Jacobian, copycat, knockoff, PWWS, BAE, TextBugger, threshold, and label-only — across tabular, image, and text modalities, with per-finding metrics, adversarial trajectory traces, and MITRE ATLAS MITRE ATLAS A MITRE-maintained knowledge base of adversarial tactics and techniques targeting AI and machine learning systems, modelled on ATT&CK, giving cyber tools a structured taxonomy for AI-specific threat modelling. /SAIF/NIST compliance mappings. Not checked yet Adds model inversion attacks that reconstruct class-representative inputs via black-box queries to surface privacy risks, completing the fourth traditional-ML attack category in AIRT. Not checked yet
+9 more
show less
Adds the ATLAS multi-agent attack framework for running adaptive campaigns against deployed multi-agent environments across three attack surfaces attack surfaces The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. , with executed tool calls captured per-trial and surfaced in findings across the UI, API, and SDK. Not checked yet Agent Output now functions as a severity-first triage workspace — searches, sorts, and filters an engagement's findings; each finding can be exported to CSV, deep-linked, or copied into a report. Not checked yet New executive/CISO CISO Chief Information Security Officer, the executive responsible for an organization's information and cyber risk strategy; cyber tools often integrate reporting or compliance features aimed at this audience. summary panel on the assessment view shows attack-surface posture, query cost to compromise, risk score, and a plain-English headline for stakeholder reporting. Not checked yet Richer privacy-attack metrics in findings: extraction findings include KL divergence and accuracy retention; membership inference includes attack accuracy, precision, and recall; model inversion includes reconstruction quality. Not checked yet New dedicated media gallery collects all images and other media logged by a session's tools in one place for reviewers. Not checked yet New web-security initial-recon skill provides structured reconnaissance for domain, wildcard, ASN ASN Autonomous System Number — a globally unique identifier assigned by regional internet registries to a network operator, letting routing protocols distinguish which organization controls a block of IP addresses. , IP-list, and CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. entry points using the ProjectDiscovery toolchain. Not checked yet Evaluation runtime now records the health of all runtime components (broken tools, skills, policies) at run time, so degraded capabilities are visible after the fact. Not checked yet Five self-contained AIRT demo notebooks cover model evasion, extraction, membership inference, jailbreaks, and multi-agent attacks — runnable via dn login with no provider keys required. Not checked yet New AI Red Teaming Learning Guide adds eight documentation pages covering all four traditional-ML attack categories and generative AI attacks, with runnable SDK, TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. , and CLI examples. Not checked yet
14 details in Everything
Traditional-ML red teaming suite — evasion, extraction, membership inference, and model inversion in one platform
seen Aug 4, 2026
·
issue 006
Dreadnode adds 20+ traditional-ML attacks, dn airt run-classifier CLI, multi-agent ATLAS campaigns, and eval agent selection to its red teaming platform.
└──▷ TRY IT
Pin a specific agent to an evaluation run so results are reproducible and the run report identifies which agent executed.
copy
$ dn evaluation create --agent <name>
Increase the number of project memories available at session start beyond the default of 20 to give agents broader context on large engagements.
copy
$ dn ... --project-memory-preload-limit 100
New dn airt run-classifier CLI command runs classic-ML attacks — evasion, extraction, membership inference, and model inversion — directly against a predict endpoint without SDK code. Not checked yet New dn evaluation create --agent <name> flag specifies which agent runs in an evaluation; eval output reports which agent actually ran. Not checked yet New --project-memory-preload-limit flag sets the number of memories preloaded at session start (range: 1–200), replacing a hardcoded default of 20. Not checked yet Adds four traditional-ML attack families (evasion, extraction, membership inference, model inversion) to AIRT, covering 20+ named attacks — including equation-solving, Jacobian, copycat, knockoff, PWWS, BAE, TextBugger, threshold, and label-only — across tabular, image, and text modalities, with per-finding metrics, adversarial trajectory traces, and MITRE ATLAS MITRE ATLAS A MITRE-maintained knowledge base of adversarial tactics and techniques targeting AI and machine learning systems, modelled on ATT&CK, giving cyber tools a structured taxonomy for AI-specific threat modelling. /SAIF/NIST compliance mappings. Not checked yet Adds model inversion attacks that reconstruct class-representative inputs via black-box queries to surface privacy risks, completing the fourth traditional-ML attack category in AIRT. Not checked yet
+9 more
show less
Adds the ATLAS multi-agent attack framework for running adaptive campaigns against deployed multi-agent environments across three attack surfaces attack surfaces The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. , with executed tool calls captured per-trial and surfaced in findings across the UI, API, and SDK. Not checked yet Agent Output now functions as a severity-first triage workspace — searches, sorts, and filters an engagement's findings; each finding can be exported to CSV, deep-linked, or copied into a report. Not checked yet New executive/CISO CISO Chief Information Security Officer, the executive responsible for an organization's information and cyber risk strategy; cyber tools often integrate reporting or compliance features aimed at this audience. summary panel on the assessment view shows attack-surface posture, query cost to compromise, risk score, and a plain-English headline for stakeholder reporting. Not checked yet Richer privacy-attack metrics in findings: extraction findings include KL divergence and accuracy retention; membership inference includes attack accuracy, precision, and recall; model inversion includes reconstruction quality. Not checked yet New dedicated media gallery collects all images and other media logged by a session's tools in one place for reviewers. Not checked yet New web-security initial-recon skill provides structured reconnaissance for domain, wildcard, ASN ASN Autonomous System Number — a globally unique identifier assigned by regional internet registries to a network operator, letting routing protocols distinguish which organization controls a block of IP addresses. , IP-list, and CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. entry points using the ProjectDiscovery toolchain. Not checked yet Evaluation runtime now records the health of all runtime components (broken tools, skills, policies) at run time, so degraded capabilities are visible after the fact. Not checked yet Five self-contained AIRT demo notebooks cover model evasion, extraction, membership inference, jailbreaks, and multi-agent attacks — runnable via dn login with no provider keys required. Not checked yet New AI Red Teaming Learning Guide adds eight documentation pages covering all four traditional-ML attack categories and generative AI attacks, with runnable SDK, TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. , and CLI examples. Not checked yet
14 details in Everything
Agent memory, triage, and session monitoring overhaul
seen Aug 4, 2026
·
issue 006
Dreadnode adds agent memory UI, five data-integration connectors, air-gapped hub sync commands, AST AST An abstract syntax tree, a structured representation of parsed code. Tools inspect or transform this tree to understand expressions and statements rather than just matching text. -based JS/TS analysis, and in-place finding triage.
└──▷ TRY IT
File a bug report from the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. immediately after a crash without losing session logs.
Adds dn capability sync and dn task sync CLI commands to pull hub content from SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. (or another on-prem) into a local directory and push it to a self-hosted instance, enabling air-gapped on-prem loading. Not checked yet Adds /report-bug command (or r in console) to the TUI, assembling a privacy-reviewed diagnostic bundle and submitting it without losing logs after a crash. Not checked yet Adds the llm-wiki capability (compiles source material into linked wiki pages) and analysis-ledger capability (maintains a resumable code-analysis frontier with evidence-bearing claims). Not checked yet Adds five data-integration connectors — Atlassian, Azure DevOps, GitHub, GitLab, and Linear — as platform capabilities. Not checked yet Adds AST-based JS/TS static analysis via ast-grep in the web-security runtime, removing the need for semgrep, CodeQL, or a jxscout license. Not checked yet
+9 more
show less
Adds an Inactive filter to Agent Sessions to isolate sessions idle past 15 minutes but not yet archived. Not checked yet New Memories page under Agents lets operators view, inspect, and manage project memory entries, including version history and diffs. Not checked yet Enables finding triage (status and notes) directly from a finding's detail panel in Agent Output. Not checked yet Session monitoring redesigned: adds a Last Msg relative-activity column, highlights sessions active in the last 15 minutes, and adds forward/backward transcript pagination with tailing mode. Not checked yet Stat cards for Needs review and Critical + High on the Agent Outputs page are now clickable filter toggles; the items grid gains a sortable Updated column. Not checked yet Sessions group-by control (None / Workflow / Capability / Agent / Source) is now available to all orgs, with workflow runs collapsed by default. Not checked yet Models and Datasets Hub browse pages add a table view alongside cards, with a unified toolbar offering separate sort and filter controls across all four Hub browse pages. Not checked yet New workspace dialog includes an organization picker to create a workspace in any org without switching context. Not checked yet Agent Output items from failed report_item POSTs are automatically recovered from span backups when a session is frozen. Not checked yet
14 details in Everything
Dreadnode August 2026 introduces air-gap mode, web-security detection capabilities, and bulk session management.
Introduces airgapped configuration profile to vendored fonts, analytics, model pricing, and pre-baked dependencies for disconnected installs Not checked yet Adds IP rotation via Cloudflare Workers in web-security capability Not checked yet Adds HTTP desync HTTP desync An attack technique that exploits disagreements between a front-end proxy and a back-end server about where one HTTP request ends and the next begins, letting an attacker poison the request queue and hijack other users' traffic. and request-smuggling detection covering 11 smuggling families in web-security capability Not checked yet Adds geo-distributed DNS resolution via Shodan or Censys in web-security capability Not checked yet Adds LSB steganography LSB steganography A data-hiding technique that encodes secret bytes into the least-significant bits of image, audio, or video samples, making changes imperceptible to human senses while preserving a covert channel inside ordinary files. on PNG images in web-security capability Not checked yet
+1 more
show less
Enables bulk archive and unarchive for agent sessions from the Sessions tab Not checked yet
6 details in Everything
Agent memory, triage, and session monitoring overhaul
Jul 30, 2026
· release notes
Dreadnode adds Inactive session filter, hub sync for air-gapped envs, AST AST An abstract syntax tree, a structured representation of parsed code. Tools inspect or transform this tree to understand expressions and statements rather than just matching text. JS/TS analysis, and direct finding triage.
└──▷ USE IT
Sync hub content to a local directory for air-gapped environments.
shell
copy
dn capability sync
Filter agent sessions to view only those idle for more than 15 minutes but not yet archived.
📍 Select Inactive from the filter dropdown in Agent Sessions
Adds dn capability sync and dn task sync commands for air-gapped on-prem loading by pulling hub content from SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. or another on-prem instance. Not checked yet Adds Inactive filter to Agent Sessions to isolate idle sessions past 15 min that are not archived Not checked yet Adds AST-based JS/TS static analysis via ast-grep in web-security runtime without semgrep, CodeQL, or jxscout license Not checked yet Enables triage of findings directly from the detail panel in Agent Output by setting status and adding notes Not checked yet
4 details in Everything
AIRT Report Builder now generally available with templates, branding, and DOCX export
seen Jul 23, 2026
·
issue 023
Dreadnode AIRT Report Builder goes GA with templates, DOCX export, new AI red-teaming skills, and a major CLI overhaul.
└──▷ TRY IT
Uninstall a capability you no longer need from your agent environment.
copy
$ dn capability uninstall <capability-name>
Update the Dreadnode CLI to the latest version without leaving your terminal.
Build and download an AIRT report in DOCX format with custom branding for client delivery.
📍 In the platform, go to AIRT › Reports, select or create a report template, configure branding (logo, company name, confidentiality footer), then click Export › DOCX.
AIRT Report Builder is now generally available for all users, with saved templates (load/save/rename/delete), custom branding (logo, company name, title, confidentiality footer), DOCX export, and a live structural preview panel. Not checked yet New trace-analysis advisor skill surfaces attack-effectiveness analysis, transform recommendations, and vulnerability pattern identification from historical run data directly inside the agent. Not checked yet New GuardSessionPolicy gates every agent tool call through an LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge before execution, with a built-in safety rubric and optional custom rules. Not checked yet GuardSessionPolicy supports five transcript strategies (rubric_only, intent_only, intent_plus_calls, full, and more) to control how much context is sent to the judge. Not checked yet New export endpoint converts session transcripts to ATIF v1.7 or OpenAI Chat Completions format; new dn session CLI command group and a session UI download menu enable browsing, inspecting, and exporting sessions. Not checked yet
+11 more
show less
New dn capability uninstall command added; session archive, freeze, and delete lifecycle actions available in the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. ; session picker rewritten with richer status columns and inline lifecycle controls. Not checked yet New dn inference-model (alias dn llm), dn secret list, and dn environment wait CLI commands added; dn env renamed to dn environment (alias retained); destructive-action --yes/-y confirmation standardized across all commands. Not checked yet New dn update command lets users update the Dreadnode CLI directly from the terminal. Not checked yet Platform admins can configure which models appear as featured in the catalog via a new admin UI, including manual entry of preview or unreleased model IDs, without code changes or redeployments. Not checked yet TUI now renders report tool calls inline with full markdown content and a clickable View in web deep-link opening the platform Reports tab for the active session. Not checked yet Agent session views and TUI footer now show tool call count and estimated USD cost alongside message count and token usage. Not checked yet The ask_user tool now supports structured multi-question bundles, explicit cancel flows (raising UserCancelled), and an interactive TUI widget with tab navigation, multi-select, and Esc-to-cancel. Not checked yet Datasets, environments, models, and capabilities now have dedicated shareable URLs; training job selections are reflected in the URL via ?job=<id>. Not checked yet Exported ATIF trajectories now include an extra.dreadnode block with origin and {id, key} pairs for organization, workspace, and project to support downstream data lineage tracing. Not checked yet Persistent TUI welcome panel now shows profile, runtime, and capability context; a new getting-started skill routes new users to the right capability or task automatically. Not checked yet Notification badges for pending org invitations now appear in the nav bar and Account Settings on login or page refresh. Not checked yet
16 details in Everything
└──▷ BREAKING ON UPGRADE
! The Export PDF Report button on the AIRT overview page has been removed; the Reports tab now handles PDF and all other export formats.! The default GuardSessionPolicy transcript strategy is now intent_plus_calls (previously unspecified/different), which changes what context is sent to the LLM judge for existing GuardSessionPolicy configurations.
Agent Output available in beta for all orgs
seen Jul 23, 2026
·
issue 023
Dreadnode adds ATLAS multi-agent attack framework, 170 multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. red-team transforms, LiteLLM on-prem inference, E2B sandbox, and a full slash-command/@ palette in web chat.
└──▷ TRY IT
Cap token spend on an evaluation run for reproducible cost control across CI pipelines.
copy
$ dn evaluation create --max-steps 50 --config evaluation.yaml
Adds ATLAS multi-agent attack framework (dreadnode.airt.atlas) running campaigns across eight attack modes using a MDP+Hedge router, with tool calls captured per-trial and surfaced in findings across the UI, API, and SDK. Not checked yet Ships 130+ image, audio, and video perturbations for red teaming vision/audio/video models, covering ImageNet-C corruptions, AugLy augmentations, SpecAugment, FigStep, and DolphinAttack techniques. Not checked yet Exposes 131 multimodal transforms in the AI red-teaming TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. (up from 26), including 57 image, 52 audio, and 22 video transforms. Not checked yet Adds slash-command palette in the web chat composer — type / for a fuzzy-filtered overlay with built-in actions (/new, /clear, /rewind, /model, /agent, and more) plus dynamically-discovered skills. Not checked yet Adds @-mention agent picker in the web chat composer, navigable by keyboard or mouse, inserting agents as inline mentions. Not checked yet
+16 more
show less
Adds /background <task> (or /bg) launcher to spin up a headless session without leaving the current conversation. Not checked yet Introduces new tool renderers in chat (glob, grep, read, query, web search), an improved session header, capability picker, and read-only session notices. Not checked yet Renames Structured Output to Agent Output throughout the UI, nav, and route (/agents/agent-outputs/); now available in beta for all orgs including on-prem/enterprise. Not checked yet Bundles LiteLLM as a Helm subchart for on-prem/enterprise installs, enabling dn/* models, TUI/chat inference, and the Admin Model Deployments surface. Not checked yet Adds E2B as a first-class on-prem sandbox provider configurable via KOTS toggle. Not checked yet Adds --max-steps / max_steps: budget parameter to dn evaluation create and evaluation.yaml for reproducible cost control. Not checked yet Adds AgentMail email inbox integration for web-security agents — list/create inboxes and list, get, send, or reply to messages. Not checked yet Adds Azure AI Foundry multimodal target support for probing text+image and text+audio deployments via the SDK and TUI. Not checked yet Adds dreadnode[nova-sonic] install extra for Nova Sonic S2S dependencies. Not checked yet Automated internal-network and Active Directory Active Directory Microsoft's directory service for Windows networks that centralises authentication and authorisation; cyber tools target or integrate with it because it controls identity and access across most enterprise environments. engagements now run end-to-end through a pipeline of specialized agents covering discovery, exploitation, credential harvesting, reporting, lateral movement lateral movement Moving from an initially compromised system or identity to other resources in a network. Attackers often use stolen credentials or trusted connections to expand their access. , and coercion. Not checked yet Blind vulnerability testing (e.g., blind SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. ) now works without external tooling, with automatic provider fallback. Not checked yet Provisions rockyou.txt, SecLists 10k-most-common.txt, and OneRuleToRuleThemAll.rule at install time for out-of-the-box hashcat and john_the_ripper support. Not checked yet Displays native reasoning_content / Anthropic thinking blocks in session transcript viewer and includes them in ATIF trajectory exports. Not checked yet TUI agent picker (Ctrl+A ) now shows the locally installed version of each capability. Not checked yet Session sharing now shows a popover with plain-language visibility state (Private / Shared with workspace) and a copyable deeplink. Not checked yet Assessment findings automatically carry target and judge model metadata inferred from configs, eliminating manual annotation. Not checked yet
21 details in Everything
└──▷ BREAKING ON UPGRADE
! The Structured Output nav item and route are renamed to Agent Output at /agents/agent-outputs/; any bookmarks or integrations referencing the old route or label will break.
Analytics query and notebook UX overhaul
seen Jul 23, 2026
·
issue 023
Dreadnode adds web chat for project runtimes, persistent web-security agent memory, and a refreshed analytics UX.
└──▷ HOW TO FIND IT
When reviewing a web-security agent run, use example query chips and schema column insertion on the analytics page to quickly build queries against persisted memory artifacts without writing SQL from scratch.
📍 In the console, go to Analytics › Query, select a schema column from the column insertion panel, or choose an example query chip to pre-populate the editor with a query against your project's reconnaissance findings or discoveries.
Adds empty states, a stats summary strip, loading skeletons, inline error banners, schema column insertion, and example query chips to the analytics query and notebook pages. Not checked yet Enables the web-security agent to persist reconnaissance findings, gadgets, leads, defense bypasses, and discoveries across sessions using structured project memory. Not checked yet Allows revealed images in tool results and logged outputs to be re-hidden, freeing the decoded blob from memory. Not checked yet
3 details in Everything
Android APK research capability and issue-tracker connectors for web-security
seen Jul 23, 2026
·
issue 023
Dreadnode adds Android APK static analysis, Jira/GitHub issue-tracker connectors, artifact logging, and admin model controls for web-security agents.
Adds android-apk-research capability bundle: a 10-tool MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server with four skills for static semantic vulnerability research on Android APKs. Not checked yet Adds Jira Cloud MCP connector for web-security agents to export validated findings directly as remediation tickets. Not checked yet Adds GitHub MCP connector for web-security agents to file findings as GitHub issues and post follow-up comments from within the agent workflow. Not checked yet Adds four artifact logging tools (log_image_output, log_audio_output, log_video_output, log_file_artifact) for attaching media and file artifacts to a web-security agent run. Not checked yet Adds waymore to the web-security capability runtime, enabling historical URL and response retrieval from Wayback Machine, CommonCrawl, OTX OTX AlienVault's Open Threat Exchange, a community platform where researchers share indicators of compromise; cyber tools integrate it to pull live threat intelligence feeds without building their own collection infrastructure. , URLScan, and VirusTotal. Not checked yet
+4 more
show less
Adds a built-in IDOR IDOR Insecure Direct Object Reference, a web vulnerability where an application exposes internal identifiers (IDs, filenames) without access checks, letting an attacker substitute another user's ID to reach their data. /BOLA BOLA Broken Object Level Authorization, an API vulnerability class where a server fails to verify that the requesting user owns or may access the object ID they supply, letting attackers read or modify other users' data. rubric for the SDK's default LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge scorer with graduated pentest-aligned cross-boundary access criteria, composable via task.yaml and SDK configs. Not checked yet Adds a live activity feed on the home page showing recent projects, sessions, evaluations, training jobs, and other workspace activity. Not checked yet Enables organization administrators to grant each member access to a specific set of AI models, enforced across the web app, API, and CLI. Not checked yet Adds an Ask an agent tab to every in-product CLI guide across all surfaces (capability, task/environment, dataset, model, evaluation, optimization, world manifest, trajectory, training). Not checked yet
9 details in Everything
Binary analysis capability replaces windows-reversing with cross-platform PE/ELF/Mach-O support
seen Jul 23, 2026
·
issue 023
Dreadnode adds cross-platform binary analysis, Android APK research, AEM/Sling web testing, and bulk evaluation log downloads.
└──▷ USE IT
Enable cross-platform binary analysis (PE/ELF ELF The standard binary format for executables, shared libraries, and object files on Linux and most Unix-like systems, giving cyber tools a predictable structure to parse, instrument, or analyze compiled code. /Mach-O) in an agent capability config, replacing the old windows-reversing bundle.
yaml
copy
capability: binary-analysis
Run static vulnerability research against an Android APK by enabling the new android-apk-research capability bundle.
yaml
copy
capability: android-apk-research
Mark an MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server header optional so OAuth runs as the default when the env var is unset.
yaml
copy
headers:
- name: Authorization
value: "Bearer ${MY_API_KEY}"
optional: true
New binary-analysis capability supports PE, ELF, and Mach-O formats with an expanded Ghidra MCP server and a consolidated 8-phase analysis skill. Not checked yet New android-apk-research capability ships a 10-tool MCP server and four skills for static semantic vulnerability research on Android APKs. Not checked yet Automated web-security testing now covers Adobe Experience Manager and Apache Sling, surfacing selector-abuse, dispatcher-bypass, and XSS XSS Cross-site scripting, an attack that runs malicious script in another user's browser through a trusted site. It can steal data or perform actions using the user's session. weaknesses. Not checked yet Bulk evaluation log download lets you export all sample logs from an evaluation as a single ZIP bundle. Not checked yet Dashboard workspace toggle lets users filter activity between personal workspace and full organization view. Not checked yet
+4 more
show less
Org owners and admins can download receipts for individual credit purchases from the billing settings page. Not checked yet MCP server headers now support optional: true so unset env vars omit the header entirely, enabling OAuth as the default without a wrapper capability. Not checked yet Server-side transcript search enables finding matches across all messages in a long session without paging through the entire transcript. Not checked yet Task verification method (script, flag, judge, or compound) is now visible in the environment task detail and evaluation sample detail views. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! The windows-reversing capability bundle is replaced by binary-analysis; any configuration referencing windows-reversing must be updated to use binary-analysis.
Claude Code engine — run Claude's agentic loop as a governed, session-backed agent
seen Jul 23, 2026
·
issue 023
Dreadnode adds Claude Code engine, Task Sets, per-role environment model selection, eval sample search, and two new offensive security skills.
└──▷ TRY IT
Override the defender (environment) model per role independently of the solver and judge, e.g. to pit a weaker defender against a stronger attacker.
copy
$ dn eval run --env-model defender=openai/gpt-4o --env-model judge=anthropic/claude-3-5-sonnet <eval-target>
Group related tasks into a versioned Task Set and run them all as one evaluation target from the CLI.
copy
$ dn task-set run <org>/<task-set-name>
Adds pluggable agent execution engines with Claude Code as the first built-in option, running Claude's agentic loop as a governed, session-backed agent with full trace viewer support. Not checked yet Introduces Task Sets — named, versioned collections of tasks runnable as a single evaluation target via the API, dn task-set CLI commands, or the Environments UI. Not checked yet Enables user-controlled task-environment models: choose which model each environment role uses via --env-model role=id (CLI), model_overrides in evaluation.yaml, or the API, independently of solver and judge models. Not checked yet Adds free-text search across all samples in an evaluation, with match highlighting, per-sample match counts, and a Matches only filter. Not checked yet Adds a blind SQL injection SQL injection An attack that makes an application treat untrusted input as part of a database command. It can expose or modify data by changing what the query does. extraction skill supporting boolean/timing-based oracle identification, WAF WAF A reverse proxy that inspects HTTP/HTTPS traffic and blocks requests matching known attack patterns such as SQL injection or XSS, sitting between clients and a web application to filter malicious input before it reaches the server. bypass patterns, and automated char-by-char extraction. Not checked yet
+5 more
show less
Extends the blind-SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. -chains skill to detect available cloud CLIs and provision attacker infrastructure (S3 buckets, redirect servers) for SSRF proof-of-concept evidence. Not checked yet Shows task-set provenance provenance Evidence recording where a software artifact came from and how it was built, including its source and build process. It helps a consumer check that the artifact matches a trusted build. (org/name and skipped members with reasons) on the evaluation detail page when an eval was run from a task set. Not checked yet Adds a model, tokens, tool calls, and cost summary to stderr in dn --print headless mode after each run. Not checked yet Displays sub-agent LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. costs as a separate subagents $X.XX segment in the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. footer. Not checked yet Running dn --resume (or -r) with no argument now opens the session picker instead of erroring. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! The --session <name> flag is now required for concurrent web-security agents; omitting it will cause agents to clobber each other's browser state.
Compound eval verification — script_and_judge and flag_and_judge
seen Jul 23, 2026
·
issue 023
Dreadnode adds compound eval verification, agentic outcome judging, 6 new web pentesting skills, and expanded AIRT goal categories.
└──▷ TRY IT
Run an agentic outcome judge against an agent trajectory to get a pass/fail verdict without writing a custom scoring script.
copy
$ dn outcome-judge run
New script_and_judge and flag_and_judge verification methods chain a mechanical check (script or flag) with an LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge to close reward-hacking gaps in eval tasks — no custom rubric required. Not checked yet New outcome_judge verification method lets eval tasks use an agentic LLM to inspect agent trajectories and emit pass/fail verdicts, exposed via the new dn outcome-judge run CLI subcommand. Not checked yet New opt-in intent_plus_outputs_summary guard strategy replaces raw tool outputs with LLM-generated summaries in judge prompts, reducing prompt-injection prompt-injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. surface while preserving tool-call context. Not checked yet Six new web app pentesting skills added: ESI injection, gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. -Web pentest, H2C/WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. smuggling, HTTP connection contamination, timing-attack recon, and XSLT injection. Not checked yet Adds waymore to the web-security capability runtime for historical URL and response retrieval from Wayback Machine, CommonCrawl, OTX OTX AlienVault's Open Threat Exchange, a community platform where researchers share indicators of compromise; cyber tools integrate it to pull live threat intelligence feeds without building their own collection infrastructure. , URLScan, and VirusTotal. Not checked yet
+4 more
show less
Free-text search in evaluation trajectories with inline match highlighting, auto-expansion of collapsed tool calls, and query state synced to the URL. Not checked yet Expanded AIRT goal categories from 9 to all 15, now including reasoning_exploitation, supply_chain, and resource_exhaustion. Not checked yet Org admins can now control which AI models each member is allowed to use from the org members admin page. Not checked yet Simplified AIRT workspace layout uses a cleaner ~/.dreadnode/airt/[org]/[workspace]/ path structure, replacing the previous env-var-based path system. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! The AIRT workspace path structure has changed to ~/.dreadnode/airt/[org]/[workspace]/, replacing the previous env-var-based path system — existing setups relying on the old env-var paths will need to be updated.
End-to-end multimodal AI red teaming — probe vision, audio, and video models with full media rendering in findings and traces
seen Jul 23, 2026
·
issue 023
Dreadnode adds end-to-end multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. AI red teaming, custom HTTP targets, Task Sets, and a SecurityContext MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server.
└──▷ USE IT
Point a PAIR attack at a private Azure OpenAI endpoint using Azure AD auth via the new custom_http target mode.
python
copy
build_target(TargetSpec(mode="custom_http", url="https://<your-resource>.openai.azure.com/openai/deployments/<deployment>/chat/completions", auth="azure_ad"))
View the README for a capability in the CLI before running it, to understand inputs, outputs, and auth requirements.
copy
$ dn capability info <capability-name> --readme
New multimodal AI red teaming: probe LLMs LLMs A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. with text, image, audio, and video inputs; apply per-modality transforms; score with the new multimodal_judge scorer; view full message parts inline in findings, traces, and parquet exports (schema v3 with base64 media columns). Not checked yet Cross-product prompt_matrix mode runs N prompts × M media items = N×M trials for systematic multimodal attack coverage. Not checked yet Nova Sonic speech-to-speech target support added to the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. capability picker and build_target SDK factory. Not checked yet New custom_http target mode and build_target(TargetSpec) factory let TAP, PAIR, and other attacks hit any endpoint (Azure, Vertex, SageMaker, Bedrock, OpenAI-compatible) with declarative auth strategies (API key, Bearer, AWS SigV4 SigV4 AWS's request-signing protocol that authenticates HTTP calls by hashing the request body, headers, and credentials into a signature; cyber tools use it to talk to AWS APIs without embedding long-lived secrets. , Azure AD, GCP). Not checked yet Per-modality response scores in findings and Assessment Findings tables, with the highest-scoring modality emphasized. Not checked yet
+15 more
show less
Structured findings and assets: agents can emit typed vulnerabilities, endpoints, and other items viewable in a new Structured Output page with per-type tables, detail panels, and provenance provenance Evidence recording where a software artifact came from and how it was built, including its source and build process. It helps a consumer check that the artifact matches a trusted build. history. Not checked yet Web-security agents now produce WebVulnerability and WebEndpoint items visible in the Items UI for triage, filtering, and cross-session tracking. Not checked yet Task Sets (V1): group multiple tasks into a named, versioned set and run evaluations against the whole set via API, CLI (dn task-set), or the Environments UI. Not checked yet Session groups and workflow hierarchies organize multi-session agent runs into collapsible workflow groups; the SDK exposes a new client.workflow() API. Not checked yet SecurityContext MCP server for web-security agents: mines commit history and CVE disclosures to generate hunting briefs and ranked vulnerability leads via three tools — get_security_context, create_security_context, get_vulnerability_leads. Not checked yet Three new web-security skills added: git-integration-exploitation, http-query-method (RFC 10008 parser differentials), and dom-vulnerability-detection (postMessage IP normalization bypass). Not checked yet Model reasoning (Anthropic thinking blocks, reasoning_content) now appears as a typed first-class field in session transcripts and ATIF trajectory exports. Not checked yet Web chat gains interactive ↔ autonomous mode toggle with optional step cap, Rewind to here control, and a full action menu (copy ID/link, export trajectory, archive/freeze/delete) from the session list. Not checked yet Web chat transcript surfaces ask_user prompts inline, renders live tool media during streaming, and exposes a reasoning-effort selector in the composer. Not checked yet Chat UI promoted to main sidebar navigation (no longer a beta route). Not checked yet New dreadnode[nova-sonic] SDK extra installs all required AWS dependencies for Nova Sonic speech-to-speech targets. Not checked yet Bundle README surfaced in frontend, TUI (d key), and CLI (--readme / -R flags on dn capability info and dn task info). Not checked yet Hub scope tabs (Mine · {org} · Public) with live count pills added to Dataset, Model, Capability, and Environment browse pages. Not checked yet New auth-setup-guide skill for AIRT walks through authenticating target, attacker, and judge models across Azure, AWS Bedrock, GCP Vertex, and custom HTTP endpoints. Not checked yet Chat sandbox keepalive: a periodic ping extends the runtime's expiry every 30 seconds while actively working, preventing mid-session auto-pause. Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! The items key in capability manifests is replaced by a unified produces key that configures built-in item types, custom types, and disablement — existing manifests using items will need to be updated.
Free-text search in evaluation trajectories
seen Jul 23, 2026
·
issue 023
Dreadnode adds free-text search in evaluation trajectories, session rewind, cross-org share links, and sandbox dependency auto-install.
└──▷ HOW TO FIND IT
Quickly locate a specific tool call or output string inside a long evaluation run without manually scrolling through every trajectory step.
📍 In the console, open an evaluation trajectory, then type your search term into the free-text search box — matching content is highlighted inline and tool calls containing the term expand automatically.
Roll back a TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. conversation to an earlier point to re-run from a known-good message without losing the full history.
Adds free-text search in hosted evaluation trajectories — matches are highlighted inline and tool calls auto-expand when their content matches the search term. Not checked yet Adds session rewind via /rewind or double-Esc in the TUI, rolling back a conversation to any prior user message while preserving full session history. Not checked yet Enables cross-org capability share links so Capability Hub links automatically redirect recipients to the correct page regardless of their org slug. Not checked yet Sandbox runtimes now auto-install Python packages and system dependencies declared in capability manifests at load time. Not checked yet AIRT CLI now auto-discovers attacks, transforms, and scorers at runtime (61 attacks, 547 transforms, 141 scorers) with accurate capability counts in the hub. Not checked yet
+3 more
show less
ATIF trajectory exports now include an extra.dreadnode block carrying org, workspace, project, and optional evaluation/item IDs for source traceability. Not checked yet Adds a copy-to-clipboard button next to the task name in the environment detail drawer for quick use in CLI commands or evaluation setup. Not checked yet Settings sidebar now groups options as Personal (Secrets, Chat Models) vs Organization for clearer separation. Not checked yet
8 details in Everything
Session and Trace Views Now Display Agent-Captured Images, Audio, and Video
seen Jul 23, 2026
·
issue 023
Dreadnode adds media playback in session views, ASM ASM Attack Surface Management: the continuous practice of discovering, inventorying, and monitoring an organization's externally exposed assets so that cyber tools can flag unknown or misconfigured entry points before attackers find them. capability, HTTP/2 HTTP/2 The second major version of the HTTP protocol, standardized by the IETF, adding multiplexed streams, header compression, and binary framing over a single TCP connection to cut latency and reduce overhead. WAF WAF A reverse proxy that inspects HTTP/HTTPS traffic and blocks requests matching known attack patterns such as SQL injection or XSS, sitting between clients and a web application to filter malicious input before it reaches the server. bypass, GraphQL pentesting, and a sandbox runtime hierarchy.
└──▷ TRY IT
Run a smoke test that mirrors production runtime and validates judge-backed tasks before submitting — catches multi-file solution issues early.
copy
$ dn task validate --smoke
Review agent-captured media artifacts from a session without auto-decoding potentially hostile content.
📍 In the platform UI, open a session transcript or trace details view, then click Show media on any image, audio, or video item to decode and display it.
Adds inline display of agent-captured images, audio, and video in session transcripts and trace details, with an explicit Show media click to prevent auto-decoding of hostile artifacts. Not checked yet New attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. management capability combining BBOT scanning, Shodan enrichment, Neo4j Neo4j A graph database maintained by Neo4j Inc. that stores data as nodes and relationships rather than tables, letting cyber tools query complex entity connections and traversal paths efficiently. graph analysis, screenshot triage, and a multi-agent ASM pipeline. Not checked yet New h2-waf-bypass skill covering 6 HTTP/2 WAF bypass classes: delayed DATA frame timing, body size truncation, Extended CONNECT, ForwardAuth body stripping, path normalization, and JSON content-type gaps. Not checked yet New graphql-pentest skill covering endpoint discovery, introspection mining, resource abuse (CWE CWE Common Weakness Enumeration, a catalog of recurring software and hardware weakness types. It describes classes of mistakes, such as injection, rather than individual vulnerability instances. -400, CWE-674), content-type CSRF CSRF Cross-site request forgery, an attack that makes a signed-in browser send an unwanted request to a site. The site may accept the request using the victim's existing session. , and capability matrix testing. Not checked yet New standalone vuln-assessment-methodology capability providing a reusable severity matrix, disprove-first rules, and reporting standards any security capability can load. Not checked yet
+8 more
show less
New --judge-model flag on dn evaluation create lets you override the task-level judge model at eval creation time without modifying task.yaml. Not checked yet ProcessJudge now supports opt-in prefix caching to reduce LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. costs on long judge sessions; GuardSessionPolicy enables it by default. Not checked yet Automated Cloud Assessments now run authorized AWS exploitation checks to validate real-world impact of exposed AWS credentials or instance-metadata findings. Not checked yet Dashboard workspace toggle lets analysts filter activity between personal workspace and full organization view. Not checked yet Pinned smoke solution image: dn task validate --smoke now runs in a container mirroring the production agent runtime. Not checked yet dn task validate --smoke now covers judge-backed verification methods (script_and_judge and flag_and_judge tasks). Not checked yet Default agent timeout for evaluations doubled from 30 minutes to 1 hour. Not checked yet Expired email verification links can now be resent in a single click from the recovery page. Not checked yet
13 details in Everything
Tool media evidence in session transcript
seen Jul 23, 2026
·
issue 023
Dreadnode adds ProjectMemory, inline media in transcripts, new DoS/path-traversal/EXIF EXIF Metadata standard embedded in image and audio files that records camera settings, timestamps, GPS coordinates, and device identifiers — giving cyber tools a rich source of attribution and forensic data without touching file content. skills, and a unified LiteLLM admin proxy.
└──▷ TRY IT
Inject secrets or config into a challenge service during smoke testing without modifying docker-compose.yaml.
copy
$ dn task validate --smoke -e API_KEY=abc123 -e TARGET_HOST=http://localhost:8080
Adds ProjectMemory tools so agents can persist and retrieve durable project-scoped memory across runs. Not checked yet Screenshots and media logged via dn.log_output() inside tools now render inline in the session transcript next to the producing tool call. Not checked yet New unified LiteLLM admin proxy lets admins manage model deployments and credentials directly from the platform; platform models are now always org-allowlist-scoped. Not checked yet Adds Ctrl+K shortcut in the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. to open the full model browser. Not checked yet New app-layer-dos skill covers ReDoS ReDoS A denial-of-service attack that exploits catastrophically backtracking regular expressions, causing a regex engine to consume exponential CPU time on crafted input; tools use detection of vulnerable patterns to flag risky code. , decompression bombs, server delay exploitation, and cross-protocol amplification for application-layer DoS testing. Not checked yet
+11 more
show less
New archive-path-traversal skill covers Zip Slip, symlink attacks, polyglot MIME bypass, and Unicode path confusion via archivealchemist tooling. Not checked yet New exiftool capability adds exif_read, exif_write, exif_strip, and exif_copy methods for EXIF metadata manipulation in web-security agents. Not checked yet AIRT Findings list now defaults to newest-first order, auto-refreshes every 20 seconds with a notification pill, and shows a structured Human Review table, Metadata tile with Finding/Assessment IDs, copy button on reasoning, and UUID UUID A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. -prefix search. Not checked yet Web-security agent now emits a STATUS update (including an Unexplored field) after every action for improved scan-coverage visibility. Not checked yet Web-security vulnerability reports now include a trace ID linking each finding back to the confidence assessment that approved it. Not checked yet The web-security credence tool now accepts an optional CVSS CVSS Common Vulnerability Scoring System, a method for describing a vulnerability's characteristics and severity. Its score is not the probability that attackers will exploit it. score, echoes it as [cvss:N.N] in output, and flags mismatches such as low confidence paired with a high CVSS score. Not checked yet ASR by Category card on the Assessments page now renders a bar chart in Charts mode. Not checked yet Home page activity feed now shows an actor chip per event; agent sessions list shows who or what started each session. Not checked yet Evaluations list now surfaces who or what ran each sample alongside the capability reference. Not checked yet New -e / --env flag on dn task validate --smoke lets you inject environment variables into the challenge service at smoke-test time without editing docker-compose.yaml. Not checked yet Adds a Release Notes page at docs.dreadnode.io/release-notes with tier chips, month navigation, per-entry permalinks, and an RSS feed. Not checked yet
16 details in Everything
Traditional-ML red teaming suite — evasion, extraction, membership inference, and model inversion in one platform
Jul 23, 2026
· release notes
Dreadnode adds CLI for traditional-ML attacks, session media gallery, model inversion, and --project-memory-preload-limit
└──▷ TRY IT
Run classic-ML attacks against a predict endpoint directly from the command line without SDK code.
copy
$ dn airt run-classifier --target https://api.example.com/predict
Specify which agent runs during an evaluation to control execution context.
copy
$ dn evaluation create --agent my_custom_agent
dn airt run-classifier CLI command Not checked yet Configurable project memory preload limit via --project-memory-preload-limit (1–200) Not checked yet Model inversion attacks as a new traditional-ML attack family with reconstruction quality metrics Not checked yet Eval agent selection via dn evaluation create --agent <name> Not checked yet A New Gallery Gathers a Session’s Captured Media in One Place Not checked yet
+3 more
show less
Web-security initial-recon skill using ProjectDiscovery for domain, wildcard, ASN ASN Autonomous System Number — a globally unique identifier assigned by regional internet registries to a network operator, letting routing protocols distinguish which organization controls a block of IP addresses. , IP-list, and CIDR CIDR A notation for a block of IP addresses, such as 10.0.0.0/24. The number after the slash says how many leading address bits identify the network. entry points Not checked yet Executive/CISO CISO Chief Information Security Officer, the executive responsible for an organization's information and cyber risk strategy; cyber tools often integrate reporting or compliance features aimed at this audience. summary panel on assessment view with attack-surface posture and query cost Not checked yet Five AIRT demo notebooks for evasion, extraction, membership inference, jailbreaks, and multi-agent attacks Not checked yet
8 details in Everything
Agent Output available in beta for all orgs
Jul 16, 2026
· release notes
Dreadnode adds slash-command chat palette, Agent Output beta for all orgs, E2B on-prem sandbox, and multi-agent ATLAS framework.
└──▷ TRY IT
Spin up a headless agent session for background tasks without leaving the current chat.
copy
$ /background <task>
Run an evaluation with a hard step limit to control costs and ensure reproducibility.
copy
$ dn evaluation create --max-steps 100
Slash-command palette in the web chat composer opened by typing / Not checked yet @ -mention agent picker in the chat composer Not checked yet /background launcher in the web chat composer to spin up headless sessions Not checked yet New Agent Output available in beta for all orgs Not checked yet dreadnode.airt.atlas module for ATLAS multi-agent attack framework Not checked yet
+5 more
show less
131 multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. transforms (image, audio, video) exposed via TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. and SDK Not checked yet LiteLLM bundled as a Helm subchart for on-prem inference Not checked yet E2B sandbox provider configurable via KOTS toggle in self-hosted installs Not checked yet --max-steps flag on dn evaluation create and max_steps key in evaluation.yaml for cost control Not checked yet AgentMail email inbox integration for web-security agents Not checked yet
10 details in Everything
End-to-end multimodal AI red teaming — probe vision, audio, and video models with full media rendering in findings and traces
Jul 9, 2026
· release notes
Dreadnode adds end-to-end multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. AI red teaming (vision/audio/video), structured output structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. page, web chat mode toggle, and Nova Sonic S2S target support
└──▷ HOW TO FIND IT
Probe a vision, audio, or video model end-to-end with automated scoring of generated media outputs
📍 dn redteam run --target build_target(TargetSpec(url='https://api.example.com/v1', auth_type='bearer') ) --scorer multimodal_judge
Install dependencies required for Nova Sonic speech-to-speech targets in your local environment
📍 pip install dreadnode[nova-sonic]
End-to-end multimodal AI red teaming — probe vision, audio, and video targets with multimodal_judge scorer, inline media rendering in findings/traces/exports (parquet schema v3 with base64 columns), cross-product prompt_matrix mode, and Nova Sonic S2S target support Not checked yet New Structured Output page for web-security agents with per-type tables for WebVulnerability and WebEndpoint items, detail panels, and provenance provenance Evidence recording where a software artifact came from and how it was built, including its source and build process. It helps a consumer check that the artifact matches a trusted build. history Not checked yet Web chat interactive ↔ autonomous mode toggle with optional step cap, Rewind to here control on prior user messages, and full action menu (copy ID/link, export trajectory, archive/freeze/delete) from session list Not checked yet Unified produces key for capability manifests, replacing the older items key Not checked yet Chat sandbox keepalive that extends runtime expiry every 30 seconds during active work Not checked yet
+12 more
show less
Full multimodal AIRT output capture with per-modality worst-case MAX score aggregation and inline audio/video playback in trace viewer Not checked yet Nova Sonic speech-to-speech target support via build_target(TargetSpec) factory and TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. capability picker Not checked yet SecurityContext MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server for web-security agents with get_security_context, create_security_context, and get_vulnerability_leads tools Not checked yet Three new web-security skills: git-integration-exploitation, http-query-method (RFC 10008 parser differentials), dom-vulnerability-detection (postMessage IP normalization bypass) Not checked yet Agent sessions default to no grouping; workflow grouping available in selector on Sessions page Not checked yet Model reasoning as first-class field in session transcripts and trajectory export (native reasoning content now appears instead of being silently dropped) Not checked yet Auth-setup-guide skill for AIRT to walk through authenticating target, attacker, and judge models across Azure, AWS Bedrock, GCP Vertex, custom HTTP endpoints Not checked yet New dreadnode[nova-sonic] SDK extra with required AWS deps for Nova Sonic speech-to-speech targets Not checked yet Custom HTTP targets via build_target(TargetSpec) factory supporting declarative auth strategies (API key, Bearer, AWS SigV4 SigV4 AWS's request-signing protocol that authenticates HTTP calls by hashing the request body, headers, and credentials into a signature; cyber tools use it to talk to AWS APIs without embedding long-lived secrets. , Azure AD, GCP) Not checked yet Hub scope tabs with live count pills on Dataset, Model, Capability, and Environment browse pages Not checked yet Bundle README surfaced in frontend, TUI (d), CLI (--readme / -R) Not checked yet Org, workspace, and project names enforce 100-character limit during input Not checked yet
17 details in Everything
└──▷ BREAKING ON UPGRADE
! The items key in capability manifests is replaced by the unified produces key! The undocumented run_in_background field has been removed from agent sessions
Claude Code engine — run Claude's agentic loop as a governed, session-backed agent
Jul 2, 2026
· release notes
Dreadnode introduces Claude Code engine, task sets, and new web-security skills
└──▷ USE IT
Group multiple tasks into a versioned collection and run them as a single evaluation target.
shell
copy
dn task-set create --name security-scan-v1 --task-id t1,t2,t3
Run an evaluation where the defender environment uses a specific model role.
shell
copy
dn eval run --env-model defender=claude-3-5-sonnet-20241022
Adds pluggable execution engine architecture with Claude Code as the first built-in option Not checked yet Adds dn task-set CLI commands to group tasks into named, versioned collections Not checked yet Adds --env-model role=id CLI argument and model_overrides config key to select defender models per role Not checked yet Adds free-text sample search with Matches only filter in evaluation UI Not checked yet Adds new blind SQLi SQLi An attack that makes an application treat untrusted input as part of a database command. It can expose or modify data by changing what the query does. extraction skill for boolean/timing-based oracle identification Not checked yet
+2 more
show less
Adds blind-SSRF-chains skill that guides agents to provision attacker infrastructure (S3, redirect servers) Not checked yet Makes --session <name> flag required for concurrent web-security agents Not checked yet
7 details in Everything
New memory UI, five integration connectors, AST AST An abstract syntax tree, a structured representation of parsed code. Tools inspect or transform this tree to understand expressions and statements rather than just matching text. -based JS/TS analysis, and air-gapped sync commands
└──▷ USE IT
Sync on-prem content from SaaS SaaS Software delivered over the internet and billed by subscription, hosted and operated by the vendor so the buyer skips installation and infrastructure management. hub to local directory.
shell
copy
dn capability sync --from saas --to ./hub-content
Adds a Memories page under Agents for viewing, inspecting, and managing project memory entries with version history and diffs. Not checked yet Adds five data-integration connectors: Atlassian, Azure DevOps, GitHub, GitLab, and Linear as platform capabilities. Not checked yet Adds AST-based JS/TS static analysis in web-security using ast-grep. Not checked yet Adds dn capability sync and dn task sync commands for air-gapped hub synchronization between SaaS and self-hosted instances. Not checked yet
4 details in Everything
Analytics query and notebook UX overhaul
Jun 25, 2026
· release notes
Dreadnode adds web chat interface, structured project memory for agent findings, and media hiding controls.
Adds a full web chat interface for querying analytics of project runtimes Not checked yet Enables the web-security agent to persist reconnaissance findings, gadgets, leads, defense bypasses, and discoveries across sessions via structured project memory Not checked yet Allows users to hide revealed images in tool results and free decoded blobs from memory Not checked yet
3 details in Everything
Tool media evidence in session transcript
Jun 18, 2026
· release notes
Dreadnode v2026-06-18 adds ProjectMemory persistence, DoS/path-traversal skills, EXIF EXIF Metadata standard embedded in image and audio files that records camera settings, timestamps, GPS coordinates, and device identifiers — giving cyber tools a rich source of attribution and forensic data without touching file content. tools, and inline media rendering
└──▷ HOW TO FIND IT
Admin manage LiteLLM model deployments and credentials directly from the platform UI.
📍 Use Ctrl+K in the TUI to open the full model browser or navigate to the unified LiteLLM admin proxy page.
Log media evidence from a tool so it appears inline in the session transcript for debugging.
python
copy
# In your custom tool or script, log output which will now render inline
import dn
dn.log_output("screenshot.png", content_type="image/png")
Adds ProjectMemory tools for persisting and retrieving durable project-scoped memory across runs Not checked yet Renders screenshots and media logged via dn.log_output() inline in the session transcript next to the tool call Not checked yet Provides a unified LiteLLM admin proxy and model browser with org-allowlist scoping and Ctrl+K TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. access Not checked yet
3 details in Everything
Session and Trace Views Now Display Agent-Captured Images, Audio, and Video
Jun 11, 2026
· release notes
Dreadnode v2026-06-11 adds media views, ASM ASM Attack Surface Management: the continuous practice of discovering, inventorying, and monitoring an organization's externally exposed assets so that cyber tools can flag unknown or misconfigured entry points before attackers find them. and pentest skills, vuln-assessment methodology, and evaluation flags.
New Session and Trace Views now display agent-captured images, audio, and video directly in the transcript (requires Show media click). Not checked yet New attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. management capability combining BBOT, Shodan, Neo4j Neo4j A graph database maintained by Neo4j Inc. that stores data as nodes and relationships rather than tables, letting cyber tools query complex entity connections and traversal paths efficiently. graph analysis, screenshot triage, and multi-agent ASM pipeline. Not checked yet New h2-waf-bypass skill in web-security covering 6 bypass classes including delayed DATA frame timing and Extended CONNECT. Not checked yet New graphql-pentest skill covering endpoint discovery, introspection mining, resource abuse (CWE CWE Common Weakness Enumeration, a catalog of recurring software and hardware weakness types. It describes classes of mistakes, such as injection, rather than individual vulnerability instances. -400, CWE-674), content-type CSRF CSRF Cross-site request forgery, an attack that makes a signed-in browser send an unwanted request to a site. The site may accept the request using the victim's existing session. , and capability matrix testing. Not checked yet New standalone vuln-assessment-methodology capability providing reusable severity matrix and disprove-first rules. Not checked yet
+2 more
show less
New --judge-model flag on dn evaluation create to override the task-level judge model without modifying task.yaml. Not checked yet Automated Cloud Assessments now measure the impact of exposed AWS credentials with authorized exploitation checks. Not checked yet
7 details in Everything
Binary analysis capability replaces windows-reversing with cross-platform PE/ELF/Mach-O support
Jun 4, 2026
· release notes
Dreadnode adds cross-platform PE/ELF ELF The standard binary format for executables, shared libraries, and object files on Linux and most Unix-like systems, giving cyber tools a predictable structure to parse, instrument, or analyze compiled code. /Mach-O binary analysis, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. header omission support, and bulk evaluation log download.
Binary-analysis capability replaces windows-reversing with cross-platform PE/ELF/Mach-O support Not checked yet Conditional MCP header omission allows headers to be marked optional: true so unset env vars omit the header entirely Not checked yet Bulk evaluation log download enables downloading all sample logs from an evaluation as a single ZIP bundle Not checked yet
3 details in Everything
Dreadnode June 2026 adds project memory, attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. management, app-layer DoS and H2 WAF WAF A reverse proxy that inspects HTTP/HTTPS traffic and blocks requests matching known attack patterns such as SQL injection or XSS, sitting between clients and a web application to filter malicious input before it reaches the server. bypass skills, media evidence rendering, smoke test env injection, and session vi
└──▷ USE IT
Inject a custom API key into the smoke test challenge service without modifying docker-compose.yaml.
shell
copy
dn task validate --smoke -e API_KEY=sk-live-xyz
View agent-captured media directly in the session transcript with explicit Show media controls.
📍 In the Dreadnode platform, navigate to Session › [Session ID] and click Show media on any logged images, audio, or video artifacts.
dn task validate --smoke -e / --env flag to inject environment variables into challenge services during smoke tests Not checked yet ProjectMemory tools for agent-persisted project-scoped memory across runs Not checked yet app-layer-dos skill covering ReDoS ReDoS A denial-of-service attack that exploits catastrophically backtracking regular expressions, causing a regex engine to consume exponential CPU time on crafted input; tools use detection of vulnerable patterns to flag risky code. , decompression bombs, server delay exploitation, and cross-protocol amplification Not checked yet archive-path-traversal skill covering Zip Slip, symlink attacks, polyglot MIME bypass, and Unicode path confusion via the archivealchemist tooling Not checked yet exif_read, exif_write, exif_strip, exif_copy methods in web-security agents for EXIF EXIF Metadata standard embedded in image and audio files that records camera settings, timestamps, GPS coordinates, and device identifiers — giving cyber tools a rich source of attribution and forensic data without touching file content. metadata manipulation Not checked yet
+3 more
show less
Attack surface management capability combining BBOT scanning, Shodan enrichment, Neo4j Neo4j A graph database maintained by Neo4j Inc. that stores data as nodes and relationships rather than tables, letting cyber tools query complex entity connections and traversal paths efficiently. graph analysis, screenshot triage, and multi-agent ASM ASM Attack Surface Management: the continuous practice of discovering, inventorying, and monitoring an organization's externally exposed assets so that cyber tools can flag unknown or misconfigured entry points before attackers find them. pipeline Not checked yet h2-waf-bypass skill in the web-security capability covering 6 bypass classes including delayed DATA frame timing, body size truncation, Extended CONNECT, ForwardAuth body stripping, path normalization, and JSON content-type gaps Not checked yet Session and Trace Views now display agent-captured images, audio, and video with explicit Show media controls instead of raw base64 Not checked yet
8 details in Everything
Android APK research capability and issue-tracker connectors for web-security
May 28, 2026
· release notes
New android-apk-research capability bundle, Jira and GitHub MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connectors, artifact logging tools, and IDOR IDOR Insecure Direct Object Reference, a web vulnerability where an application exposes internal identifiers (IDs, filenames) without access checks, letting an attacker substitute another user's ID to reach their data. /BOLA BOLA Broken Object Level Authorization, an API vulnerability class where a server fails to verify that the requesting user owns or may access the object ID they supply, letting attackers read or modify other users' data. judge rubric for Dreadnode.
android-apk-research capability bundle ships with a 10-tool MCP server and four skills for static semantic vulnerability research on Android APKs Not checked yet New Jira MCP connector lets web-security agents export validated findings directly to Jira Cloud as remediation tickets Not checked yet New GitHub MCP connector lets web-security agents file findings as GitHub issues and add follow-up comments without leaving the agent workflow Not checked yet Four new path-based logging tools for web-security agents: log_image_output, log_audio_output, log_video_output, and log_file_artifact to attach screenshots, audio, video, and file artifacts directly to a run Not checked yet New built-in IDOR/BOLA rubric available for the SDK’s default LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge scorer with graduated pentest-aligned cross-boundary access criteria Not checked yet
+2 more
show less
Home page now shows a live activity feed with recent projects, sessions, evaluations, training jobs, and other workspace activity Not checked yet Organization administrators can grant each member access to a specific set of AI models, enforced across the web app, API, and CLI Not checked yet
7 details in Everything
Compound eval verification — script_and_judge and flag_and_judge
May 21, 2026
· release notes
New compound eval verification strategies (script_and_judge, flag_and_judge) and an agentic outcome judge for Dreadnode
script_and_judge and flag_and_judge are new eval task verification methods that chain mechanical checks with an LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. outcome judge to close reward-hacking gaps. Not checked yet New dn outcome-judge run CLI subcommand exposes the agentic outcome_judge verification method for inspecting agent trajectories and emitting pass/fail verdicts. Not checked yet New opt-in policy introduces the intent_plus_outputs_summary guard strategy, replacing raw tool outputs with LLM-generated summaries in judge prompts to reduce prompt-injection prompt-injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. surface. Not checked yet Six new web-security capability skills are now available as knowledge distillations: ESI injection, gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. -Web pentest, H2C/WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. smuggling, HTTP connection contamination, timing-attack recon, and XSLT injection. Not checked yet waymore is added to the web-security capability runtime for historical URL and response retrieval from Wayback Machine, CommonCrawl, OTX OTX AlienVault's Open Threat Exchange, a community platform where researchers share indicators of compromise; cyber tools integrate it to pull live threat intelligence feeds without building their own collection infrastructure. , URLScan, and VirusTotal. Not checked yet
+1 more
show less
Organization admins can now control which AI models each member is allowed to use via a new setting on the org members admin page. Not checked yet
6 details in Everything
Free-text search in evaluation trajectories
May 14, 2026
· release notes
Free-text search, session rewind, cross-org shares, and auto-installing sandbox deps in Dreadnode.
Adds free-text search in hosted evaluation trajectories with inline match highlighting and auto-expanding tool calls. Not checked yet Adds /rewind subcommand and double-Esc keybinding to roll back a conversation session history via the TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. . Not checked yet Enables cross-org capability share links that automatically redirect recipients to the correct page regardless of their org slug. Not checked yet Enables sandbox runtimes to auto-install Python packages and system dependencies declared in capability manifests at load time. Not checked yet
4 details in Everything
AIRT Report Builder now generally available with templates, branding, and DOCX export
May 7, 2026
· release notes
Dreadnode GA: Report templates, DOCX export, GuardSessionPolicy with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. tool gating, dn CLI overhaul
AIRT Report Builder graduates to general availability with saved templates (load/save/rename/delete), custom branding support (logo, company name, title, confidentiality footer), and DOCX export Not checked yet GuardSessionPolicy gates every agent tool call through an LLM judge before execution using a built-in safety rubric and optional custom rules Not checked yet GuardSessionPolicy supports five transcript strategies (rubric_only, intent_only, intent_plus_calls, full) to control judge context Not checked yet New dn session CLI command group and export endpoint convert session transcripts to ATIF v1.7 or OpenAI Chat Completions format Not checked yet Added dn capability uninstall command, dn inference-model (alias dn llm), dn secret list, dn environment wait, and dn update commands Not checked yet
+1 more
show less
Platform admins can configure featured catalog models via a new admin UI setting without code changes Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! dn env is renamed to dn environment (alias retained)
Dreadnode May 2026: Android APK research capability, Jira/GitHub MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connectors, artifact logging tools, and compound eval verification
└──▷ USE IT
Run a web-security evaluation using compound verification to prevent reward hacking.
shell
copy
dn task validate --method flag_and_judge --task my-eval-task.yaml
dn outcome-judge run --trajectory /path/to/trajectory.json
Attach logs and artifacts to a web-security agent run.
shell
copy
log_image_output ./screenshot.png
log_file_artifact ./debug.log
android-apk-research capability bundle with a 10-tool MCP server for static semantic vulnerability research on Android APKs Not checked yet Jira MCP connector lets web-security agents export validated findings to Jira Cloud as remediation tickets Not checked yet GitHub MCP connector lets web-security agents file findings as GitHub issues and add follow-up comments Not checked yet Four new path-based logging tools for web-security agents: log_image_output, log_audio_output, log_video_output, and log_file_artifact to attach artifacts to runs Not checked yet New built-in IDOR IDOR Insecure Direct Object Reference, a web vulnerability where an application exposes internal identifiers (IDs, filenames) without access checks, letting an attacker substitute another user's ID to reach their data. /BOLA BOLA Broken Object Level Authorization, an API vulnerability class where a server fails to verify that the requesting user owns or may access the object ID they supply, letting attackers read or modify other users' data. rubric for the SDK’s default LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. judge scorer with graduated pentest-aligned cross-boundary access criteria Not checked yet
+4 more
show less
dn task validate now accepts flag_and_judge and script_and_judge compound verification methods Not checked yet dn outcome-judge run CLI subcommand exposes outcome_judge agentic verification method for inspecting agent trajectories Not checked yet Six new web app pentesting skills in the web-security capability: ESI injection, gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. -Web pentest, H2C/WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. smuggling, HTTP connection contamination, timing-attack recon, and XSLT injection Not checked yet waymore integration added to web-security capability runtime for historical URL and response retrieval from Wayback Machine, CommonCrawl, OTX OTX AlienVault's Open Threat Exchange, a community platform where researchers share indicators of compromise; cyber tools integrate it to pull live threat intelligence feeds without building their own collection infrastructure. , URLScan, and VirusTotal Not checked yet
9 details in Everything