PAGES
Subscribe Get it delivered — five to ten releases we picked each morning from the tools you run, with every release in the issue on the web. Compare plans →

The Cyber Toolchain — issue 008, July 8, 2026

THE CYBER TOOLCHAIN NO. 008
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED JULY 8, 2026 · EVERY DAY
EDITIONS tail grep head ls diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

We read every release from the 1309 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW
ISSUE VIEW scroll
ISSUE WIDTH reading width
Do you prefer scroll?
ADDITIONAL FILTERS
$ tct list   # 10 tools matched
Network Security
◆  Firewalls & Network Defense

Cloudflare

Your Worker can now have its own cache in front of it (2026-07-06)

Cloudflare Blog is an official publication sharing updates, technical insights, and announcements about Cloudflare's internet security, performance, and networking products and services.

Cloudflare Workers Cache adds a tiered cache in front of Workers, configured via Wrangler and standard Cache-Control headers.

└──▷ USE IT
Enable Workers Cache for a Worker so Cloudflare's cache layer handles repeat requests before your code runs, eliminating CPUCPUThe main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. cost on cache hits.
json
{
  "name": "my-worker",
  "main": "src/index.ts",
  "compatibility_date": "2026-05-01",
  "cache": {
    "enabled": true
  }
}
Serve a server-rendered page at cache speed for most visitors while keeping content fresh — fresh for 5 min, stale-served for up to 1 hour while background revalidation runs.
javascript
return new Response(html, {
  headers: {
    "Content-Type": "text/html; charset=utf-8",
    "Cache-Control": "public, max-age=300, stale-while-revalidate=3600",
  },
});
Purge cached entries for a specific product after an inventory update, without touching any other Worker's or zone's cached content.
javascript
await ctx.cache.purge({ tags: ["product:123"] });
  • New Workers Cache: a tiered cache that sits in front of a Worker, enabled with a single cache.enabled block in wrangler.toml, so cacheable requests never invoke Worker code or incur CPU billing.
  • Supports stale-while-revalidate — stale responses are served instantly while the Worker re-renders in the background, so no user ever waits on a cache refresh.
  • Supports standard Vary header for content negotiation, storing separate cache variants per distinct header combination (e.g., Accept, Accept-Language) with no allowlist restrictions.
  • New ctx.cache.purge() API enables Workers to programmatically purge their own cache by tag (tags: ["product:123"]), path prefix, or everything — scoped to the Worker entrypoint, not the zone.
  • Cache follows the Worker, not the hostname — a single Worker's cache is shared across custom domains, workers.dev, service bindings, preview URLs, and Workers for Platforms tenants.
+2 more show less
  • Per-entrypoint cache control: Workers for Platforms tenants each get an isolated cache; preview deployments each get their own cache partition, preventing test traffic from polluting production.
  • Multi-tenant-safe cache keys via ctx.props allow shaping the cache key programmatically without zone-level Cache Rules or Page Rules.

7 details in Everything

Was this useful?
Cloud & Container Security
◆  Cloud Security Posture

Prowler

5.33.0

Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment.

Prowler 5.33.0 adds agentic Lighthouse AI assistant, credential-free compliance PDFs, and scan queueing.

└──▷ GET THIS VERSION
$ git clone --branch 5.33.0 https://github.com/prowler-cloud/prowler.git
# already have the repo? check out this version:
$ git checkout 5.33.0
  • New Lighthouse AI agentic assistant (Prowler Cloud/Enterprise) queries findings, compliance posture, and risky resources using configurable LLMLLMA 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. providers (OpenAI, Amazon Bedrock, or any OpenAI-compatible endpoint).
  • Persistent chat sessions with real-time streaming, session history, archiving, and a sidebar chat mode accessible from any page in the Prowler Cloud UI.
  • Compliance PDF reports now generate without active provider credentials, drawing on provider metadata stored in the database.
  • Overlapping scans for the same provider now queue behind the active scan instead of running concurrently, eliminating duplicate or racing scan workers.
  • Kubernetes provider rejects kubeconfigs using exec authentication in Prowler Cloud, blocking user-supplied commands from executing on Cloud workers.

5 details in Everything

Was this useful?
Exposure & Vulnerability Management
◆  Vulnerability Management

Rapid7 Insight Platform

Cloud Security (InsightCloudSec) Release Notes (2026-07-07)

Rapid7 Insight Platform is a cloud-based security operations platform that unifies vulnerability management, detection, response, and threat intelligence across an organization's IT environment.

InsightCloudSec 26.7.7 adds ASG/EBSEBSAmazon's block-storage service for EC2 instances, providing persistent network-attached volumes that survive instance restarts and can be snapshotted, giving cyber tools durable, scalable disk without managing physical drives./Security Group insights, enhanced credential cleanup, and CISCISA nonprofit that publishes consensus-based configuration benchmarks and controls for hardening operating systems, cloud environments, and software; cyber tools use it as a ready-made compliance baseline. RHOCP v1.9.0 benchmark support.

  • New Insights added for Auto Scaling Groups, EBS Volumes, and Security Groups.
  • Enhanced credential cleanup capabilities.
  • Adds support for CIS Red Hat OpenShift Container Platform Benchmark v1.9.0.

3 details in Everything

Was this useful?

defectdojo

3.1.0

Open-Source Unified Vulnerability Management, DevSecOps & ASPM

DefectDojo 3.1.0 adds new parsers, JIRA multi-component support, AES-256-GCMAES-256-GCMAES encryption in Galois/Counter Mode, which encrypts data and detects tampering in one pass. It is the default cipher for TLS and most disk and cloud encryption. credential encryption, and import/deduplication sync control.

└──▷ GET THIS VERSION
$ git clone --branch 3.1.0 https://github.com/DefectDojo/django-DefectDojo.git
# already have the repo? check out this version:
$ git checkout 3.1.0
  • Adds Garak (NVIDIA LLMLLMA 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. vulnerability scanner) parser for AI/LLM security findings.
  • Adds Govulncheck Scanner V2 parser for Go vulnerability results.
  • Adds PICUS Breach and Attack Simulation CSV parser.
  • Supports multiple JIRA components in project settings.
  • Supports CVSSCVSSCommon Vulnerability Scoring System, a method for describing a vulnerability's characteristics and severity. Its score is not the probability that attackers will exploit it. vector parsing and severity derivation in the cargo-audit parser.
+14 more show less
  • Includes analysis.detail from Dependency Track FPF in finding descriptions.
  • Modernizes Tool Config credential encryption to AES-256-GCM.
  • New setting allows import/reimport to wait for deduplication to complete before returning.
  • New setting allows disabling and dismissing the open source message banner.
  • Adds global required fields notice for WCAG H90 accessibility compliance.
  • Shows vulnerability IDs in PDF Reports.
  • New UI: animates collapse panels in the new UI.
  • New UI: smooth filter category accordion in the new UI.
  • New UI: folds Finding Groups under Findings in the sidebar.
  • Performance: batch Vulnerability_Id inserts during import for faster ingestion.
  • Performance: batch BurpRawRequestResponse inserts during import.
  • Performance: adds SLASLAA formal agreement between a service provider and customer that defines expected uptime, response times, and remedies for failures, giving cyber tools a contractual baseline for availability and support commitments. expiration date index for global finding list queries.
  • Performance: adds partial indexes for authorized finding-list queries.
  • Performance: drops blanket DISTINCT from FindingViewSet list for faster API responses.

19 details in Everything

Was this useful?
Build
◆  AI Coding Agents

Claude Code

v2.1.202

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Claude Code v2.1.202 adds dynamic workflow sizing, OTelOTelAn open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. workflow attributes, and a new /code-review command for multi-agent PR review.

└──▷ GET THIS VERSION
$ git clone --branch v2.1.202 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:
$ git checkout v2.1.202
└──▷ TRY IT
Run a thorough multi-agent review on a PR when you want deeper analysis than the default single-pass review.
$ /code-review high 4821
Tune agent parallelism for a complex workflow without hitting a hard cap — useful before kicking off a large refactor.
📍/config
  • Adds a Dynamic workflow size setting in /config to guide how many agents Claude spawns for dynamic workflows (small/medium/large) — advisory, not an enforced cap.
  • Adds workflow.run_id and workflow.name OpenTelemetryOpenTelemetryAn open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. attributes to telemetry from workflow-spawned agents, enabling full reconstruction of a workflow run from OTel data.
  • Introduces /code-review <level> <pr#> for multi-agent PR review at a chosen effort level; /review <pr> reverts to a fast single-pass review.
  • Improves /workflows agent list layout with wider titles, a dedicated time column, and shorter model names.
  • Improves MCPMCPModel 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. error messages to suggest "type": "http" when a server config has url but no type.

5 details in Everything

Was this useful?

Cline

cli-v3.0.38

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Cline CLI v3.0.38 refreshes the plan/act UI palette, rethinks chat input styling, and raises the default context windowcontext windowThe maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. for under-specified models to 128K.

└──▷ GET THIS VERSION
$ git clone --branch cli-v3.0.38 https://github.com/cline/cline.git
# already have the repo? check out this version:
$ git checkout cli-v3.0.38
  • New plan/act accent palette: act mode switches to blue (#79b8ff) and plan mode to amber, replacing the old cyan/yellow — applied across dialogs, model selector, config, onboarding, markdown, and syntax highlighting with light-theme contrast variants.
  • Restyled chat input: minimal full-width horizontal-rule frame with a bold accent prompt glyph (❯) and slimmer user-message bubbles, replacing the tinted background.
  • Assistant markdown accents are now tinted by the plan/act mode in which they were produced.
  • Thinking-level picker now defaults its cursor to Medium instead of Off.
  • Models in the live catalog that don't report a context window now default to a 128K input-token limit instead of 4K, giving under-specified models a usable context budget.
+1 more show less
  • Supports malformed read_files input from weaker models: orphaned start_line/end_line array entries are coalesced back onto the preceding file path rather than rejected.

6 details in Everything

Was this useful?

OpenHands

cloud-1.41.0 2 releases · 2026-07-06 LatestStable

OpenHands: AI-Driven Development

OpenHands 1.41 adds API key time windows, parallel tool calls, org admin dashboard, and semantic file chunking.

└──▷ GET THIS VERSION
$ git clone --branch cloud-1.41.0 https://github.com/OpenHands/OpenHands.git
# already have the repo? check out this version:
$ git checkout cloud-1.41.0
└──▷ TRY IT
Create an API key that is only valid within a specific time window — useful for temporary contractor access or scheduled automation.
$ curl -X POST https://app.openhands.ai/api/api-keys \
  -H 'Authorization: Bearer <your-token>' \
  -H 'Content-Type: application/json' \
  -d '{"name": "ci-bot", "not_before": "2026-08-01T00:00:00Z", "expires_at": "2026-08-31T23:59:59Z"}'
Check what permissions your service account has within an organization before attempting privileged operations.
$ curl -X GET https://app.openhands.ai/api/organizations/<org-id>/me \
  -H 'Authorization: Bearer <your-token>'
Enable parallel tool calls in agent settings to let the agent execute multiple tools concurrently and reduce round-trip latency on complex tasks.
📍In the console, go to Settings › Agent and set tool_concurrency_limit to the desired maximum number of concurrent tool calls (e.g. 4).
  • Adds semantic file chunking via tree-sitter ASTASTAn 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. parsing for more accurate code context in agent sessions.
  • New organization conversation admin dashboard lets org admins review and manage all conversations across their org.
  • Captures production workspace state as an initial snapshot on start and archives it before deletion.
  • Adds super roles via user.role_id with permission fallback for enterprise/auth authorization.
  • Exposes caller permissions on GET /organizations/{id}/me so clients can check what actions they're allowed to take.
+6 more show less
  • Adds optional active-window fields (not_before and expires_at) to API keys for time-bounded credentials.
  • Makes unbound org scope an explicit first-class option when creating API keys.
  • Adds parallel tool calls support via tool_concurrency_limit in agent settings to speed up multi-tool workloads.
  • Adds dynamic marketplace support for plugin registration, enabling third-party plugin discovery.
  • Accepts api_key cookie as a fallback credential for SaaSSaaSSoftware delivered over the internet and run on the provider's infrastructure, so the buyer pays a subscription instead of installing or operating anything locally. auth flows.
  • Attaches repo and branch metadata to Laminar traces for better observability of agent runs.

11 details in Everything

1 more release in this issue · 2026-07-06
1.9.0 Stable

OpenHands 1.9.0 adds Azure DevOps resolver, multi-model discovery, MCPMCPModel 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. config for ACP agents, sub-agent visualizer, and org admin tooling.

└──▷ GET THIS VERSION
$ git clone --branch 1.9.0 https://github.com/OpenHands/OpenHands.git
# already have the repo? check out this version:
$ git checkout 1.9.0
└──▷ USE IT
Hide personal workspaces on an org-only OHE install so users only see org workspaces.
ini
OH_HIDE_PERSONAL_WORKSPACES=true
OH_DEPLOYMENT_MODE=enterprise
Set a per-deployment resolver label and restrict resolver to enterprise cloud mode.
ini
OH_RESOLVER_LABEL=my-team-resolver
OH_DEPLOYMENT_MODE=enterprise_cloud
Switch the LLMLLMA 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. model mid-conversation for a cloud ACP agent via the proxy endpoint.
$ curl -X POST https://<your-openhands-host>/api/acp/switch_acp_model \
  -H 'Authorization: Bearer <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{"conversation_id": "<conversation_id>", "model": "gpt-4o"}'
  • Adds hide_personal_workspaces flag for org-only OHE installs to enforce org-scoped workspaces.
  • New switch_acp_model proxy endpoint enables model switching for cloud ACP conversations.
  • Adds model dropdown and credential fields to the ACP agent settings page.
  • Adds validation for secret names to ensure valid environment-variable format.
  • Exposes copyable invite links so org invitations work without email delivery.
+33 more show less
  • Auto-accepts invitation links on click, removing the confirm/cancel modal.
  • Accepts pending invitations by verified-email match at sign-in.
  • New explicit OH_DEPLOYMENT_MODE flag gates cloud-account CTAs to enterprise cloud deployments.
  • OHE multi-model LLM discovery with BYOKBYOKBring Your Own Key — a cloud deployment model where the customer supplies and controls the encryption keys rather than the provider, so sensitive data stays under the customer's cryptographic authority. gating: proxy discovery, catalogue union, and updated UX.
  • Allows MCP server configuration for ACP agents.
  • Exposes the Automations menu item to all users.
  • Persists and injects per-user OAuth tokens in Jira DC resolver conversations.
  • Adds DynamicRemoteSandboxSpecService backed by runtime-API warm configs for dynamic sandbox specs.
  • Parallelizes GitHub GraphQL queries in get_suggested_tasks for faster task suggestions.
  • Surfaces a clear error when a custom sandbox image's agent-server SDK version mismatches.
  • New OH_RESOLVER_LABEL env var enables per-deployment resolver macro overrides.
  • Supports Slack attachments in agent conversation context.
  • Adds sub-agent task (TaskToolSet) visualizer to the chat UI.
  • New Full Git history user setting controls how much repository history is provided to the agent.
  • New enterprise admin user-provisioning endpoint for programmatic user management.
  • Uses interrupt endpoint for agent pause, enabling cleaner pause/resume from the UI.
  • Adds default_sandbox_spec_id to user settings for per-user default sandbox selection.
  • Azure DevOps integration: resolver mentions and org-level one-click webhook setup.
  • Jira DC: email-mode auto-link, targeted repo lookup, and picker mentions.
  • Implements semantic file chunking using tree-sitter ASTASTAn 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. parsing for improved code context.
  • New organization conversation admin dashboard for org-level conversation oversight.
  • Captures production workspace state with an initial snapshot at start and archive before delete.
  • API keys gain an optional active window via not_before and expires_at fields.
  • Adds tool_concurrency_limit setting to agent configuration for parallel tool calls.
  • Makes unbound org scope an explicit, first-class option for API keys.
  • Adds dynamic marketplace support for plugin registration.
  • SaaSSaaSSoftware delivered over the internet and run on the provider's infrastructure, so the buyer pays a subscription instead of installing or operating anything locally. auth now accepts api_key cookie as a fallback credential.
  • New super-roles via user.role_id with permission fallback for enterprise auth.
  • Exposes caller permissions on GET /organizations/{id}/me.
  • First signed-in user is automatically made the default org owner, tracked via is_default flag.
  • Moves existing users into the default org when first auto-added.
  • Routes unclaimed automation events to the default org on single-org installs.
  • Adds repo/branch metadata to Laminar trace entries for better observability.

38 details in Everything

Was this useful?

OpenCode

v1.17.14

The open source coding agent.

Adds a code-mode MCPMCPModel 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. adapter for confined orchestration scripting, an OpenAPIOpenAPIA vendor-neutral specification for describing REST APIs in a machine-readable format, maintained by the OpenAPI Initiative. Cyber tools use it to auto-generate clients, documentation, and validation from a single source of truth. tool adapter, and a gated execute tool for code-mode sessions.

└──▷ GET THIS VERSION
$ git clone --branch v1.17.14 https://github.com/anomalyco/opencode.git
# already have the repo? check out this version:
$ git checkout v1.17.14
  • Adds a code-mode MCP adapter enabling confined orchestration scripts to run against connected MCP tools.
  • Adds an OpenAPI tool adapter for code-mode, expanding available tool integrations.
  • Gates the execute tool behind a code-mode flag so it only surfaces when code mode is active.
  • Desktop: adds recently closed projects to the Home screen for quick re-entry.
  • Desktop: adds reopening of closed tabs and background tab opening.
+5 more show less
  • Desktop: shows draft server status in the title bar.
  • Desktop: overhauled v2 review panel for improved session review workflows.
  • Desktop: improves model search in picker dialogs.
  • Desktop: makes tab navigation respond on mouse down in the new layout.
  • TUITUIA 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.: adds a debug info dialog with copy-to-clipboard support.

10 details in Everything

Was this useful?

Windsurf

updated · Jul 7, 2026

Windsurf is an AI-powered code editor that helps developers write, edit, and navigate code faster using intelligent autocomplete and agentic AI assistance.

Windsurf snapshot-20260707 adds reviewable diffs in autonomous mode, /mcp status panel, sandbox exclusion config, and ACU usage tracking.

└──▷ TRY IT
Check live MCPMCPModel 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 connectivity and status mid-session to confirm tools are available before delegating an agentic task.
$ /mcp
Review current ACU consumption to stay within quota before kicking off a long autonomous run.
$ /usage
Allow a specific high-trust command (e.g., a deployment script) to run outside the sandbox at the team level so it isn't blocked by the sandbox proxy.
📍In Settings › Team Settings, add the command under sandbox.excluded with the desired allow/ask/deny value.
  • Adds reviewable diffs for edits produced in Devin Local autonomous mode, enabling structured review before changes are applied.
  • Skill permissions: frontmatter now applies to auto-approvals, enabling fine-grained control over which skills are auto-approved.

2 details in Everything

Was this useful?
Platforms & Utilities
◆  General Utilities & Libraries

arsenal-ng

v1.5

The classic launcher, evolved. Fast, Go-based command library equipped with 200+ cybersecurity cheat-sheets.

arsenal-ng v1.5 expands its built-in cheatsheet library, growing to 242 tools and 2,872 commands.

└──▷ GET THIS VERSION
$ git clone --branch v1.5 https://github.com/halilkirazkaya/arsenal-ng.git
# already have the repo? check out this version:
$ git checkout v1.5
Was this useful?
browse all tools → score card for your toolchain →