The week in full · Jul 6–12

Web Application Security · 2026-07-12

DOMPurify 3.4.12 adds support for new SVG attributes alongside hardened handling of declarative partial updates.

• Supports additional SVG attributes, expanding the set of valid SVG markup that passes through sanitization.
• Strengthens handling of declarative partial updates to reduce exposure from incremental DOM mutation patterns.

Web Application Security · 2026-07-12

ffuf v2.2.0 adds audit logging to record all fuzzing activity for compliance and review.

• Adds audit logging functionality to record fuzzing sessions for compliance, review, and reporting purposes.

Web Application Security · 2026-07-12

XSRFProbe v3 rebuilds the CSRF engine with 25 categorized checks, headless-browser SameSite bypasses, and JSON reporting.

• Adds a full battery of 25 named checks (D1–A1) covering token tampering, method/Content-Type overrides, Origin/Referer bypasses, SameSite cookie analysis, and token strength — each with a unique ID, severity rating, and exploitability notes.
• New token-tampering checks (T2–T8) actively probe GET↔POST method switching, token omission, empty values, cross-session replay, double-submit cookies, and custom-header token forgery.
• New Origin/Referer bypass checks (R0–R2c, O1–O3) test header removal, regex tricks, subdomain tricks, and Origin: null against real-world validation implementations.

AI Coding Agents · 2026-07-11

Auto mode goes GA on Bedrock/Vertex/Foundry, Opus 4.8 becomes the default, and plugin config scoping tightens.

• Auto mode is now generally available on Bedrock, Vertex AI, and Foundry without the CLAUDE_CODE_ENABLE_AUTO_MODE opt-in flag; disable it via disableAutoMode in settings.
• Bedrock, Vertex, and Claude Platform on AWS now default to Claude Opus 4.8.
• Auto mode config is now read exclusively from ~/.claude/settings.json; the repo-resident .claude/settings.local.json autoMode key is no longer honored (breaking change for teams using per-repo overrides).

AI Coding Agents · 2026-07-11

GCP Vertex provider gains new Claude models and a free-form model ID entry field.

• Adds new Claude model IDs to the GCP Vertex provider, including claude-sonnet-5, claude-opus-4-x variants, claude-haiku-4-5, and claude-fable-5.
• Enables free-form model ID entry in the Vertex provider's model dropdown, letting practitioners use any Vertex-hosted model without waiting for an extension release.

Firewalls & Network Defense · 2026-07-11

Cloudflare Smart Tiered Cache now supports cloud region hints for AWS, GCP, Azure, and Oracle Cloud anycast origins.

• Adds cloud region hint configuration for anycast origins, letting Smart Tiered Cache select optimal upper tiers for origins on AWS, GCP, Azure, and Oracle Cloud.
• New Origin Configuration table in the dashboard (Caching > Tiered Cache > Origin Configuration) enables per-IP region hint assignment or bulk editing of all origin IPs at once.
• Supports region hint management via Cloudflare API and Terraform for infrastructure-as-code workflows.

Firewalls & Network Defense · 2026-07-11

DLP source code detection targets whole-file uploads only; new Durable Object namespaces must use SQLite backend

• Improves DLP source code detection to evaluate only whole source code file uploads/downloads, reducing false positives from code embedded in chat messages, docs, or code samples.
• Adds a 500-character minimum threshold for DLP source code file evaluation, filtering out small fragments that lack enough context for reliable classification.
• Supports confidence level tuning on DLP source code profiles to balance false-positive reduction against detection coverage in Gateway HTTP policies.

AI Coding Agents · 2026-07-11

Cursor adds side chats, agent transcript search, new cloud agent hooks, and redesigned project/repo pickers.

• New Side Chats: open parallel agent conversations via /side, /btw, or the plus button without interrupting the main agent thread — each is a durable, full agent conversation that can be revisited and @-mentioned.
• Adds agent transcript search in the Agents Window via Cmd+K (command palette), with a local search index that scales to thousands of conversations.
• Adds in-conversation search with Cmd+F, match counter, and jump-between-matches for long agent transcripts.

AI Coding Agents · 2026-07-11

Cursor 3.11 adds side chats, searchable agent transcripts, and new cloud agent hooks for conversation-level control.

• New side chats let you open parallel agent conversations (via /side, /btw, or the plus button) without interrupting the main agent thread, with full context sharing and durable follow-up.
• Adds searchable agent transcript index (Cmd+K from the command palette) that scales to thousands of conversations, plus in-conversation search (Cmd+F) with match counter and jump navigation.
• New cloud agent hooks — beforeSubmitPrompt, afterAgentResponse, afterAgentThought, stop, subagentStart, and more — enable observation and control of prompts, responses, reasoning, subagents, compaction, and turn completion.

Container & Image Security · 2026-07-11

Docker Compose v5.3.0 adds native support for pre-start init containers.

• Supports pre-start init containers, allowing services to declare initialization containers that run and complete before the main service starts.

Container & Image Security · 2026-07-11

Docker Compose v5.2.0 introduces a new reconciliation algorithm and a rawsetenv message type for provider plugins.

• New reconciliation algorithm aligns observed state with expected state more accurately during docker compose up and related operations.
• Adds rawsetenv message type for provider plugins, enabling plugins to set environment variables without shell interpolation.

Runtime Security · 2026-07-11

Docker Sandboxes v0.35.0 adds SOCKS5 proxy support, policy inspection/check commands, secret import, and a daemon management CLI.

• Adds SOCKS5 upstream-proxy transport (socks5:// / socks5h://) for sandbox egress via DOCKER_SANDBOXES_PROXY, HTTP_PROXY, or HTTPS_PROXY, with optional auth and DOCKER_SANDBOXES_NO_PROXY exclusions.
• New sbx policy inspect command to examine policy details.
• New sbx policy check network command to test whether the current policy would allow a network access request before executing.

Runtime Security · 2026-07-11

Docker Sandboxes v0.34.0 adds a native SSH endpoint, kit source allowlisting, OCI v2 streaming, and a new onboarding command.

• New experimental native SSH endpoint in sandboxd: connect with ssh <sandbox-name>@127.0.0.1 -p 2222 (publickey auth, connect-to-create, interactive shell and exec).
• New experimental sbx setup command imports agent credentials from environment variables for smoother first-time onboarding.
• Adds OCI v2 kit artifact streaming that decompresses layers once to a cache directory and uses seek-based random access, reducing memory pressure during kit reads.

Runtime Security · 2026-07-11

sbx v0.33.0 adds named sandbox identity, DNS-gated network policy, wildcard secrets, and Cursor OAuth support.

• New --name flag for sbx run identifies a sandbox independently of the working directory, enabling multiple named sandboxes in the same workspace and re-attachment from any directory.
• sbx ls --json now reports a stable per-sandbox id field for scripting and automation.
• Sandbox DNS resolution is now gated on network policy, closing a DNS-based data-exfiltration channel (CVE-2026-12039); loopback names remain exempt.

Reverse Engineering · 2026-07-11

jadx v1.5.6 adds graph views with code pane sync, a call graph library, and resource tree improvements.

• Adds graph views with code pane synchronization in the GUI for visual code flow analysis.
• New call graph module/library enables programmatic traversal of method call relationships.
• Collapses single-child directory chains in the resource tree for cleaner navigation.

AI Agent Frameworks · 2026-07-11

LangGraph CLI now supports prebuild images for langgraph deploy.

• Supports prebuild images when running langgraph deploy, enabling faster deployments using pre-built Docker images.

Integrated & IT Risk Management · 2026-07-11

LogicGate Spring 2026 introduces seven AI Workflow Agents, AI Governance module, expanded Spark AI, and enterprise-wide search across GRC use cases.

• Launches seven new AI Workflow Agents in early access spanning Third-Party Risk Management, Enterprise Risk Management, Business Continuity Management, and AI Governance use cases.
• New AI Governance module provides a unified view of AI risk: maps the full AI ecosystem, auto-calculates risk levels using NIST AI RMF categories, and surfaces business-impact indicators aligned to the EU AI Act and NIST frameworks.
• Adds Reporting Insights to Spark AI, enabling analysis of large data volumes within a single report with guided next-action recommendations.

Integrated & IT Risk Management · 2026-07-11

LogicGate unveils Config Newton agentic GRC engineer and four new workflow agents for TPRM and AI governance.

• Introduces Config Newton, an agentic GRC engineer that interprets complex program requirements, navigates Risk Cloud, and autonomously builds complete GRC programs.
• New Third-Party Risk Management Agents automatically route vendors based on risk signals, complete formal assessments, and flag findings for human-led remediation.
• New AI Governance Agents triage incoming AI use cases, score them against your risk framework, and surface recommended mitigations for human review.

Endpoint Security (EDR/XDR) · 2026-07-11

LiveKd 5.65 restricts dump file access to admins; ZoomIt 11.11 adds JPEG and WEBP snip format support.

• LiveKd now protects generated kernel dump files from being read by non-admin users.
• ZoomIt adds JPEG and WEBP format support for snip captures.

AI Coding Agents · 2026-07-11

OpenHands 1.46 adds configurable BYOR key alias patterns and enriched final archive manifests.

• Supports configurable Bring-Your-Own-Router (BYOR) key alias patterns for enterprise deployments.
• Enriches final archive manifests with additional metadata and removes redundant initial snapshots.

AI Coding Agents · 2026-07-11

Pi v0.80.6 adds a max thinking level for GPT-5.6/Claude and input-token pricing tiers for long-context cost accounting.

• Adds max thinking level (above xhigh) for GPT-5.6 and adaptive Claude models, available via CLI, SDK, RPC, and model selection; custom themes can define thinkingMax.
• Adds request-wide input-token pricing tiers for accurate long-context cost accounting (e.g. GPT-5.4/5.5/5.6 rates), configurable in models.json and modelOverrides.
• Supports ~ (home directory) expansion in the shellPath setting.

AI Coding Agents · 2026-07-11

Pi v0.80.3 adds Claude Sonnet 5, Azure Foundry endpoints, new RPC session APIs, and configurable editor/padding settings.

• Adds Anthropic Claude Sonnet 5 support via Anthropic-compatible and Bedrock provider catalogs, with adaptive thinking enabled.
• Supports modern Microsoft Azure Foundry endpoint URLs for the Azure OpenAI Responses provider.
• New get_entries and get_tree RPC commands let clients inspect session entries and tree snapshots programmatically.

AI Coding Agents · 2026-07-11

Pi v0.80.0 adds Ctrl+J newline keybinding and migrates pi-ai's global API to a new compat entrypoint.

• Adds Ctrl+J as a default newline keybinding alongside Shift+Enter.
• Moves pi-ai's legacy global API (stream/complete/completeSimple, getModel/getModels/getProviders, registerApiProvider, getEnvApiKey, etc.) from the @earendil-works/pi-ai root to @earendil-works/pi-ai/compat; extension sources typechecking against pi-ai's published types should update imports accordingly or migrate to the new createModels()/provider-factory API.
• Removes the @earendil-works/pi-ai/base and @earendil-works/pi-agent-core/base selective-provider entrypoints; use the root packages with explicit Models provider factories instead.

AI Coding Agents · 2026-07-11

Extension compaction events gain reason/willRetry context; pi update now pins the exact checked version.

• Adds reason and willRetry metadata to session_before_compact and session_compact extension events, enabling extensions to distinguish manual /compact, threshold auto-compaction, and overflow retry flows.
• Updates pi update to install the exact version returned by the Pi update check and surface the changelog URL in update notices, making upgrade behavior predictable.

AI Coding Agents · 2026-07-11

Pi v0.79.9 adds chat-template thinking support for vLLM/Hugging Face providers like DeepSeek and improves GLM-5.2 routing.

• Adds chat-template thinking support: OpenAI-compatible custom providers can now map Pi thinking levels into chat_template_kwargs, enabling vLLM/Hugging Face models such as DeepSeek to use provider-native thinking controls.
• Enables GLM-5.2 xhigh reasoning on OpenRouter and corrects Fireworks routing to use the OpenAI-compatible Chat Completions endpoint with reasoning_effort support.

AI Coding Agents · 2026-07-11

Pi v0.79.8 adds Mistral prompt caching, OpenRouter Fusion alias, and post-compaction token estimates.

• Adds Mistral prompt caching using the Pi session ID as the cache key, with cached-token usage and cost accounting surfaced per session.
• Adds openrouter/fusion as a built-in OpenRouter model alias for direct use as a provider target.
• Adds estimated post-compaction token counts to compact results and compaction events, letting clients display approximate context reduction.

AI Coding Agents · 2026-07-11

Pi v0.79.7 adds automatic light/dark theme switching, scoped update control, and new extension API exports.

• Adds automatic theme mode in /settings to assign separate light and dark themes that follow terminal color-scheme changes.
• Changes pi update to update only pi by default; new pi update --all updates pi and all extensions together.
• Exports generateDiffString, generateUnifiedPatch, and EditDiffResult from the public API for extensions that produce edit-style diffs.

Detection Engineering · 2026-07-11

Stratus Red Team v2.34.0 adds Azure App Service credential harvesting, a controllable logger API, and a threat-intel coverage mapping skill.

• New Azure attack technique: Retrieve App Service Publishing Credentials (azure.credential-access.app-service-publishing-credentials).
• New pkg/stratus/log package exposes a controllable logger, letting library embedders route Stratus log output through any slog.Handler (e.g., zap, logrus).
• New map-threat-intel-coverage agent skill fetches a threat-intelligence report, extracts cloud TTPs, classifies each against existing Stratus Red Team coverage, and drafts GitHub issues for gaps.

Compliance Automation & Trust Management · 2026-07-11

Vanta June 2026 adds audit commenting, MCP expansion, AIUC-1 pilot, CrowdStrike CSPM, Twilio integration, and 20 new privacy MCP tools.

• Adds threaded, @mention-enabled commenting on individual controls directly within a Vanta audit, replacing out-of-band email and Slack threads.
• Enables one-click export of the full controls table from within a Vanta audit for direct use in audit reports.
• Expands Vanta MCP connectivity to any MCP-capable tool (not just officially supported ones), with a warning banner when the redirect URL is outside Vanta-controlled origins.

AI Coding Agents · 2026-07-11

• Skill permissions: frontmatter definitions now apply to auto-approvals.
• Enterprise login policies are now enforced in the CLI.
• Adds server-level MCP tool permission options: approve all tools on a server for the current session, or permanently.

AI Coding Agents · 2026-07-10

Claude Code v2.1.206 adds smarter /cd suggestions, /doctor CLAUDE.md trimming, broader push-remote support, and faster background agent upgrades.

• Adds directory path tab-completion to /cd, matching the existing /add-dir behavior.
• New /doctor check analyzes checked-in CLAUDE.md files and proposes trimming content Claude can already derive from the codebase.
• Extends /commit-push-pr to auto-allow git push to the repo's configured remote.pushDefault (or the sole remote when only one exists), not just origin.

Firewalls & Network Defense · 2026-07-10

Cloudflare adds dynamic retry delays for Workflows, DNS Firewall dashboard settings, R2 SQL editor, and npm dependency telemetry for Workers.

• Supports dynamic delay functions in Workflows step retries — pass a function to retries.delay to calculate adaptive wait times based on the failed attempt context and thrown error (e.g., wait longer on rate-limit errors, shorter on transient network failures).
• Exposes DNS Firewall cluster settings — attack mitigation, rate limiting, negative TTL, and resolver subnet — directly in the Cloudflare dashboard (previously API-only); also adds a refreshed cluster table with resizable/hideable columns and a modernized create/edit form.
• Adds a built-in R2 SQL editor in the Cloudflare dashboard for querying R2 Data Catalog tables interactively, with syntax highlighting, autocomplete, result export, and EXPLAIN output.

AI Coding Agents · 2026-07-10

Crush v0.84.0 adds session-affinity headers for provider-side prompt caching.

• Sends x-session-affinity and x-session-id headers with every request, enabling supporting providers to pin sessions to a replica and maximize prompt cache hits.

Reconnaissance & OSINT · 2026-07-10

httpx v1.10.0 adds duplicate custom request headers, IP-aware deduplication, and automatic HTTP_PROXY env var support.

• Supports sending duplicate custom request headers in a single request (e.g., multiple X-Forwarded-For values).
• Adds IP-aware deduplication to filter results that resolve to the same IP across different hostnames.
• Automatically honors HTTP_PROXY/HTTPS_PROXY environment variables when -proxy flag is not explicitly set.

AI Coding Agents · 2026-07-10

Kiro adds hooks on agent file writes, lazy MCP OAuth, and multi-window settings sync in v1.0.116.

• New hooks trigger on agent-driven file writes, enabling automation to react to AI-generated file changes.
• Lazy MCP authentication automatically handles OAuth sign-in for MCP servers that require it, removing manual auth steps.
• Multi-window settings sync keeps configuration consistent across multiple open Kiro windows.

AI Coding Agents · 2026-07-10

Kiro MCP OAuth now supports pre-registered apps with client secrets, custom redirect URIs, and DCR bypass.

• Supports clientSecret in MCP OAuth config for servers that require a client secret (e.g., Figma).
• Enables skipping Dynamic Client Registration when a custom clientId is provided, authenticating as your own pre-registered app.
• Accepts full URLs with custom paths in the redirectUri field (e.g., http://localhost:7778/oauth/callback) to match exact registered callback URLs.

AI Coding Agents · 2026-07-10

Codex CLI v0.144.0 adds a writes approval mode, default MCP auth elicitation, Ultra concurrency warnings, and richer usage-limit credit details.

• Adds writes app-approval mode that permits declared read-only actions automatically while prompting only for write operations.
• Enables MCP tool interactive authentication by default — no experimental opt-in required.
• Adds runtime Codex authentication support for app-server hosts, with redirect to a hosted page on successful login.

AI Coding Agents · 2026-07-10

Adds a model-specific system prompt for Meta Muse Spark to improve coding agent responses.

• Adds a tailored system prompt for the Meta Muse Spark model, enabling more accurate and model-optimized responses when using that provider.

AI Coding Agents · 2026-07-10

OpenCode v1.17.17 adds a v2 free-model selector, dismissible tabs intro popup, and refreshed sub-agent task and revert-dock UI.

• Adds a v2 free-model selector with faster access to more providers in the desktop app.
• Introduces a dismissible tabs intro popup and a refreshed help entry point in the desktop UI.
• Updates sub-agent task rows to match the v2 session design, with distinct icon states for running, completed, and resting tasks.

AI Coding Agents · 2026-07-10

OpenHands 1.11.0 adds Agent Profiles, a Budgets dashboard, expanded usage monitoring, and email provider visibility.

• Adds Agent Profiles on the cloud/SaaS backend, enabling enterprise teams to define and manage reusable agent configurations.
• Introduces a Budgets dashboard and expands the Usage Dashboard with new spend and consumption metrics.
• New budgets and usage monitoring UI surfaces cost and utilization data directly in the product.

AI Coding Agents · 2026-07-10

OpenHands 1.45 adds Agent Profiles, a Budgets dashboard, expanded Usage dashboard, and email delivery status surfacing.

• New Agent Profiles support on the cloud/SaaS backend lets enterprises define and manage reusable agent configurations.
• New Budgets dashboard enables teams to set and monitor spending limits across agent usage.
• Expanded Usage Dashboard provides broader visibility into agent activity and resource consumption.

AI Coding Agents · 2026-07-10

OpenHands 1.44.0 adds repository metadata to observability traces for richer pipeline monitoring.

• Includes repository metadata (e.g., repo name, branch, commit) in observability traces, enabling richer filtering and attribution in tracing backends.

CNAPP · 2026-07-10

InsightCloudSec 26.7.7 adds new insights for Auto Scaling Groups, EBS Volumes, and Security Groups, plus CIS Red Hat OpenShift Benchmark v1.9.0.

• Adds new Insights covering Auto Scaling Groups, EBS Volumes, and Security Groups for expanded cloud misconfiguration detection.
• Supports CIS Red Hat OpenShift Container Platform Benchmark v1.9.0 for container platform compliance assessments.

Detection Engineering · 2026-07-10

20 new Sigma detection rules added, including TanStack supply-chain attack coverage, CVE-2026-41089, and NTLM hash leak via Curl.

• New rule: Detects APT malware signatures via antivirus telemetry.
• New rule: Detects remote access tool signatures via antivirus telemetry.
• New rule: Detects AppLocker 'application would have been blocked' audit events.

Container & Image Security · 2026-07-10

Snyk Container expands runtime detection to more JVM base images and adds .NET application dependency scanning.

• Detects Java runtime version across a wider range of JVM base images in container scans.
• Identifies vulnerabilities in .NET application dependencies within container images.

Identity & Access Management · 2026-07-10

SPIRE v1.15.2 adds SPIFFE Broker, PQC curve support, per-caller rate limiting, and TLS-secured Prometheus metrics.

• Adds configurable JTI claim inclusion in JWT-SVIDs at the entry level.
• Introduces experimental per-caller rate limiting for the agent Workload API and Envoy SDS.
• Adds TLS support for the Prometheus metrics endpoint using a SPIRE SVID, with an optional SPIFFE ID allowlist.

Secrets Detection & Management · 2026-07-10

TruffleHog v3.95.9 adds 7 new secret detectors and archived-repo exclusion for GitHub org scans.

• New OpenRouter detector identifies sk-or-v1- API keys and validates them against the OpenRouter API.
• New New Relic Insights Insert Key detector matches NRII- prefixed keys with live verification via the Events API.
• New Duffel Token detector for the Duffel travel API.

AI Coding Agents · 2026-07-10

Devin Desktop snapshot-20260710 adds sandbox exclusion controls, reviewable diffs, ACU usage visibility, and a plugin system for extending Devin Local.

• Adds New session in space option to the session kebab menu for quicker task-scoped session creation.
• Enables auto-reconnect for Devin Cloud sessions when network connectivity is restored.
• Supports copying images from chat via the context menu.

Post-Exploitation · 2026-07-09

BloodHound v9.4.0 adds ADCS ESC14 detection, new graph/relationship APIs, webhook creation, auditor role expansions, and ingest metrics.

• Adds ADCS ESC14 Scenario A attack path coverage for certificate-based privilege escalation detection.
• New GET api/v2/relationships/{relationship_id} endpoint for retrieving individual graph relationship details.
• New GET node endpoint (api/v2/...) for retrieving individual graph node details.

AI Coding Agents · 2026-07-09

Claude Code v2.1.205 upgrades /doctor into a full setup checkup, hardens auto mode safety rules, and improves the agents view.

• Adds auto mode rule that blocks tampering with session transcript files.
• Improves auto mode to prompt for confirmation before running rm -rf on an unresolvable variable, reducing accidental data loss.
• Upgrades /doctor into a full setup checkup that can both diagnose and fix issues; adds /checkup as an alias.

AI Coding Agents · 2026-07-09

Claude Code v2.1.203 adds login-expiry warnings, manual-mode visibility, MCP roots updates, and a VSCode remote-control toggle.

• Adds a pre-expiry warning when your login session is about to expire, letting you re-authenticate before background sessions are interrupted.
• Adds a grey ⏸ badge in the footer when manual permission mode is active, so the current permission mode is always visible.
• Exposes the session's additional working directories in MCP roots/list, and sends notifications/roots/list_changed whenever that set changes — enabling MCP servers to stay in sync with multi-root workspaces.

AI Coding Agents · 2026-07-09

ClinePass gains a limit-reached error with one-click billing switch and a free model picker with Subscribed/Free tabs.

• Adds a ClinePass limit-reached error with a one-click option to switch to Cline usage-based billing.
• Enables selecting Cline free models on the ClinePass provider, organized into Subscribed and Free tabs with model descriptions.

AI Coding Agents · 2026-07-09

ClinePass now supports free model selection; detached hub daemon gains telemetry with user_id identity.

• Adds support for selecting Cline free models in the ClinePass provider via the model picker.
• Enables telemetry emission from the detached hub daemon process, with telemetry identity now including user_id.
• Sends versioned client-identity headers with all Cline provider requests.

Firewalls & Network Defense · 2026-07-09

Cloudflare adds IPsec downgrade protection, WebSocket Logpush analytics, Moondream 3.1 vision model, and AI Search/Drop improvements.

• Adds key query parameter to the AI Search list items endpoint for exact object-key lookups without paging through results.
• Extends Workers AI toMarkdown (and AI Search ingestion) to support .gif and .bmp image formats.
• Introduces IPsec downgrade protection (beta) via the IKE_SA_INIT_FULL_TRANSCRIPT_AUTH IKEv2 extension for WAN and Magic Transit tunnels, guarding against quantum-capable on-path attackers.

AI Agent Frameworks · 2026-07-09

CrewAI 1.15.2 adds inline skill definitions, templated Flow action inputs, stream frame protocol, and AgentExecutor feedback handling.

• Supports inline skill definitions, eliminating the need for separate skill files in crew/flow configurations.
• Adds templated Flow action inputs, enabling dynamic parameterization of Flow actions at runtime.
• Defines a stream frame protocol for Flows, enabling structured streaming output from Flow executions.

AI Coding Agents · 2026-07-09

Crush v0.83.0 adds GPT-5.6 support, routing it through the Responses API.

• Adds GPT-5.6 model support, routed through the OpenAI Responses API.

AI Coding Agents · 2026-07-09

Crush v0.82.0 adds preserved newlines in expanded tool output and Alibaba US region support.

• Preserves newlines in expanded tool content in the chat UI, improving readability of multi-line tool outputs.
• Adds Alibaba (United States) as a supported provider region, configurable via ALIBABA_US_API_KEY.

AI Coding Agents · 2026-07-09

Gemini CLI v0.50.0 adds tool registry discovery for MCP integrations.

• Adds tool registry discovery, enabling automatic detection and registration of available tools/MCP integrations.

Web Application Security · 2026-07-09

humble 1.63 adds HAR file analysis via -if and a new insecure header check.

• Supports analyzing HAR (HTTP Archive) files as input via the -if option, enabling offline inspection of captured browser traffic.
• Adds 1 new insecure header check, expanding detection coverage.

Local LLM Runtimes · 2026-07-09

Ollama v0.31.2 adds flash attention on Pascal GPUs, iGPU vision-model offload, and privacy-hardened Claude Code launch.

• Enables flash attention on older NVIDIA Pascal GPUs (compute capability 6.x), unlocking faster inference on GTX 10-series and similar cards.
• Enables iGPU to offload vision models with padding to fit available memory, broadening multimodal support on integrated graphics.
• Disables Claude Code telemetry, error reporting, feedback commands, and non-essential traffic by default when using ollama launch claude.

AI Coding Agents · 2026-07-09

Codex CLI adds pnpm install detection, writes-app approval mode, and serialized MCP OAuth credential stores.

• Adds a writes app approval mode for the Rust CLI, giving practitioners finer-grained control over which file-write operations require explicit approval.
• Emits canonical TurnItem::CommandExecution lifecycle events from shell tool and /shell command paths, aligning app-server v2 command tracking.
• Emits canonical TurnItem::DynamicToolCall lifecycle events from dynamic tool handlers, replacing legacy request/response events.

AI Coding Agents · 2026-07-09

Codex CLI v0.143.0 adds remote plugins by default, system proxy support, daemon pairing codes, new Bedrock models, and richer app-server APIs.

• Enables remote plugins by default, with richer catalog rows, npm marketplace sources, and visible remote/local version info.
• Supports routing authentication and Responses API traffic through macOS and Windows system proxies, including PAC and WPAD configurations.
• Adds codex remote-control pair subcommand for generating manual pairing codes from a running daemon.

AI Coding Agents · 2026-07-09

Adds Ultra concurrency warning, proxy-aware WebSocket connector, MCP tool snapshot reuse, and Windows sandbox runtime access.

• Adds a TUI warning when Ultra reasoning is selected with high multi-agent concurrency (≥8 threads), displaying configured thread and subagent limits so users understand cost implications.
• Adds a proxy-aware WebSocket connector that respects outbound proxy policy and custom-CA trust, matching the same effective HTTP proxy configuration used for REST calls.
• Reuses a single MCP tool snapshot within each sampling request, reducing latency and ensuring consistent tool state between Apps World State and tool-router construction.

AI Coding Agents · 2026-07-09

Codex CLI v0.144.0-alpha.1 adds pnpm install detection, faster branch picker, and hook execution tracing.

• Detects Codex installs managed by pnpm, surfacing pnpm status in codex doctor output alongside npm and bun.
• Speeds up the /review branch picker by switching branch enumeration to git for-each-ref scoped to refs/heads, preventing timeouts in large repos.
• Adds trace spans around configured hook command execution, making slow installed hooks visible directly in traces.

AI Coding Agents · 2026-07-09

Adds writes approval mode, serialized MCP OAuth credential stores, canonical turn item emission, and improved Windows URL safety detection.

• Adds writes approval mode for MCP app tool approval, giving practitioners a middle ground between auto and prompt that gates only write operations
• Emits canonical TurnItem lifecycle events for command execution, dynamic tool calls, sub-agent activity, collab tool calls, and collab wait items, enabling more structured agent event streams
• Enables auth elicitation by default, so authentication prompts are surfaced automatically without manual configuration

AI Coding Agents · 2026-07-09

OpenCode v1.17.16 adds inline file browser tabs, a draft-preserving composer add menu, and per-session review state persistence.

• Adds inline file browser tabs in the review pane for opening and previewing files without leaving the session.
• Adds a composer add menu for inserting files, commands, context, and shell mode while preserving draft text.
• Adds an Open containing folder action for projects on the home screen.

AI Coding Agents · 2026-07-09

OpenHands 1.10.0 adds SMTP email service, user login tracking, and a renamed Usage & Monitoring dashboard.

• Adds SMTP email service integration, enabling email delivery alongside the existing Resend provider.
• Surfaces email-enabled status in the UI for both SMTP and Resend configurations.
• Tracks user login timestamps, giving admins visibility into account activity.

AI Coding Agents · 2026-07-09

OpenHands cloud-1.43.0 adds SMTP email service, user login tracking, and a renamed Usage & Monitoring dashboard.

• Adds SMTP email service integration, enabling transactional email delivery alongside the existing Resend provider.
• New email-enabled status surface shows whether SMTP or Resend email is active in the platform configuration.
• Tracks user login timestamps, giving admins visibility into last-active data per user.

AI Coding Agents · 2026-07-09

OpenHands 1.9.1 adds a super-admin management API for granting, revoking, and listing admin privileges.

• New enterprise/auth super-admin endpoint enables granting, revoking, and listing super-admin roles via API.

AI Coding Agents · 2026-07-09

OpenHands cloud-1.42.0 adds a super-admin management API for granting, revoking, and listing admin privileges.

• New enterprise super-admin management endpoint enables granting, revoking, and listing super-admin roles via API.

CNAPP · 2026-07-09

Prisma AIRS 3.0 adds Japan local cloud region, AI Agent SSPM, AI Red Teaming, and expanded model/runtime scanning.

• New local cloud region in Japan for Prisma AIRS, enabling data residency and low-latency processing for Japanese enterprises.
• New AI Agent SSPM (SaaS Security Posture Management) detects and governs agentic threats including identity impersonation, memory manipulation, and tool misuse across autonomous AI assistants.
• New AI Red Teaming capability performs automated, adaptive penetration tests against AI deployments using an agent that learns and evolves like a real attacker.

Attack Surface & Exposure Management · 2026-07-09

Qualys CSAM integrates with Cisco Cloud Control, exposing asset inventory, TruRisk scores, and remediation workflows to Cisco AI agents.

• New Cisco Cloud Control integration connects Qualys Unified Asset Inventory, TruRisk Prioritized Findings, and remediation workflows into Cisco's AI Canvas environment.
• Cisco AI agents can now query Qualys at runtime — pulling asset inventory, vulnerability detections per host/workload, TruRisk scores, exploit context, and triggering remediation or mitigation workflows as typed tool calls.
• Enables cross-domain asset and risk visibility spanning cloud, network, identity, datacenter, and security domains without manual tool-switching.

Vulnerability Management · 2026-07-09

Qualys Patch Management adds autonomous zero-day remediation via TruRisk Eliminate and Windows 11 upgrade orchestration through QQL and CAR scripts.

• New autonomous remediation workflows via Qualys TruRisk Eliminate enable machine-speed patching, mitigation, container image replacement, workload isolation, and firewall policy updates triggered directly from confirmed vulnerability findings.
• Supports patchless/compensating mitigation actions when immediate patching is not feasible, reducing exposure window while permanent fixes are prepared.
• Enables enterprise-wide Windows 11 upgrade orchestration through TruRisk Eliminate, covering three paths: enablement packages, ISO-based feature updates, and direct Windows 10-to-Windows 11 upgrades.

Detection Engineering · 2026-07-09

sigma-cli v3.1.0 adds JUnit XML export and per-rule file output with directory structure preservation.

• Adds JUnit XML export for sigma convert results, enabling CI pipeline integration with standard test reporting tools.
• Adds --output-dir and --output-filename-template flags to write each converted rule to a separate file, with optional preservation of the source directory hierarchy.

CNAPP · 2026-07-09

Wiz ASM adds automated subdomain recon, API endpoint discovery, runtime sensor telemetry, and custom target input to map attack surface.

• Adds automated subdomain reconnaissance seeded from owned root domains to surface shadow exposures.
• Discovers REST API endpoints via cloud-native API gateways, Wiz Runtime Sensor telemetry, and Attack Surface Scanner-detected API specifications.
• Leverages Wiz Runtime Sensor inbound network traffic telemetry to identify and assess active endpoint exposure.

Runtime Security · 2026-07-09

Wiz Defend adds AI coding assistant context-aware detections for symlink and SSH key attacks at clone and write time.

• Detects malicious symlinks pointing to sensitive files at git clone time, catching GhostApproval-style attacks before AI coding assistant involvement.
• Monitors writes to sensitive files (e.g., SSH authorized_keys) at write time, triggering alerts regardless of whether the write originates via a symlink.
• Adds AI agent context awareness: alerts auto-elevate severity when malicious activity originates from an AI coding assistant process operating on untrusted repositories.

Data Security & DLP · 2026-07-09

Zscaler Workflow Automation adds end-user DLP triage, self-service email quarantine release, and automated exception management.

• Adds end-user justification workflows that engage users directly via Slack, Microsoft Teams, or email when an inline DLP policy triggers, routing responses to auto-remediation, manager escalation, or analyst enrichment.
• Enables manager-approved, time-bounded DLP policy exceptions created automatically through workflow responses — no manual policy edits required.
• Introduces Release Email Quarantine action in the advanced incident details interface, letting admins deliver quarantined messages to all or specific recipients directly from the platform.

CNAPP · 2026-07-09

Zscaler Posture Control adds AI-SPM with shadow AI discovery, drift detection, and automated red teaming mapped to MITRE ATLAS, NIST AI RMF, and OWASP LLM Top 10.

• New AI Security Posture Management (AI-SPM) provides continuous discovery and posture assessment of AI assets including shadow AI, unsanctioned models, embedded SaaS AI, developer-built agents, and MCP servers.
• New AI Bill of Materials (AI-BOM) maps model lineage across discovered AI assets for full supply-chain visibility.
• Adds posture assessment for AI-specific risks: misconfigurations, excessive permissions, vulnerable RAG frameworks, and exposed data pipelines.

General Utilities & Libraries · 2026-07-08

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

• Adds new pentest tools to the built-in cheatsheet library, bringing the total to 242 tools and 2,872 commands.

AI Coding Agents · 2026-07-08

Claude Code v2.1.202 adds dynamic workflow sizing, OTel workflow attributes, and a new /code-review command for multi-agent PR review.

• 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 OpenTelemetry 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.

AI Coding Agents · 2026-07-08

Cline CLI v3.0.38 refreshes the plan/act UI palette, rethinks chat input styling, and raises the default context window for under-specified models to 128K.

• 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.

Firewalls & Network Defense · 2026-07-08

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

• 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.

Firewalls & Network Defense · 2026-07-08

Cloudflare adds RDP file transfer controls, Browser Isolation for auth proxy endpoints, a new /accessibilityTree API, R2 Data Catalog delete warnings, and self-serve virtual appliance registration.

• Adds file transfer controls for browser-based RDP (beta): restrict upload, download, both directions, or disable entirely per Access policy — useful for BYOD and contractor scenarios.
• Enables Browser Isolation HTTP Isolate policies on authorization proxy (PAC file) endpoints, supporting identity-based isolation without requiring the Cloudflare One Client.
• New Browser Run /accessibilityTree endpoint delivers the browser's structured accessibility tree (roles, names, states, hierarchy) directly to AI agents and automation workflows.

Vulnerability Management · 2026-07-08

DefectDojo 3.1.0 adds new parsers, JIRA multi-component support, AES-256-GCM credential encryption, and import/deduplication sync control.

• Adds Garak (NVIDIA LLM 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.

Endpoint Security (EDR/XDR) · 2026-07-08

Microsoft Defender now includes an Active Directory domain investigation page with security posture and trust relationship visibility.

• New Active Directory domain investigation page surfaces domain properties, deployment health, identity summary, service account breakdown, sensitive entities, active recommendations, group policies, and trust relationships.

AI Coding Agents · 2026-07-08

Adds a code-mode MCP adapter for confined orchestration scripting, an OpenAPI tool adapter, and a gated execute tool for code-mode sessions.

• 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.

AI Coding Agents · 2026-07-08

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

• 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.

AI Coding Agents · 2026-07-08

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

• Adds semantic file chunking via tree-sitter AST 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.

Cloud Security Posture · 2026-07-08

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

• New Lighthouse AI agentic assistant (Prowler Cloud/Enterprise) queries findings, compliance posture, and risky resources using configurable LLM 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.

Vulnerability Management · 2026-07-08

InsightCloudSec 26.7.7 adds ASG/EBS/Security Group insights, enhanced credential cleanup, and CIS 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.

AI Coding Agents · 2026-07-08

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

• 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.

Web Application Security · 2026-07-06

BunkerWeb v1.6.12 adds upstream TLS verification, per-path mTLS, a full logs viewer overhaul, and tightened API token security.

• Adds upstream HTTPS certificate verification for reverse proxy via REVERSE_PROXY_SSL_VERIFY, REVERSE_PROXY_SSL_VERIFY_DEPTH, REVERSE_PROXY_SSL_TRUSTED_CERTIFICATE, REVERSE_PROXY_SSL_TRUSTED_CERTIFICATE_DATA, and REVERSE_PROXY_SSL_TRUSTED_CERTIFICATE_PRIORITY settings.
• Adds MTLS_URL_n regex setting to enforce mTLS selectively per path rather than site-wide.
• Adds SCHEDULER_MAX_WORKERS to cap the job-executor thread pool and reduce database pool pressure under load.

Cloud Security Posture · 2026-07-06

Cloudsplaining 0.9.0 adds 37 new privilege-escalation detections linked to pathfinding.cloud.

• Adds 37 new privilege-escalation path detections integrated with pathfinding.cloud, surfaced and linked directly in the HTML report.
• Enriches the built-in example dataset to produce a higher-quality demo report with more representative findings.

Endpoint Security (EDR/XDR) · 2026-07-06

CTFd 3.8.6 adds admin UI and API support for reclassifying correct submissions as incorrect.

• New Admin Panel UI to mark a previously correct submission as incorrect.
• PATCH /api/v1/submissions/[submission_id] now supports marking submissions as incorrect via the API.

Web Application Security · 2026-07-06

Dalfox v3.1.1 unifies server/MCP scan target params, consolidates debug logging, and bounds request fan-out for safer large scans.

• Unifies scan target parameter: Server and MCP modes now accept target (REST retains url as a backward-compatible alias).
• Consolidates all debug output through a single stderr dbg_log! macro, keeping JSON/JSONL/SARIF stdout clean under --debug.
• Aligns OOB/blind XSS lifecycle messages with the standard timestamped log format (INF/WRN/OOB), making output consistent across scan modes.

Web Application Security · 2026-07-06

Dalfox v3.1.0 adds blind/OOB XSS, HAR input, external JS analysis, CSP/Trusted Types payloads, and a global rate limiter.

• Adds --blind-oob for out-of-band (OAST) XSS detection via interactsh, catching stored and async sinks that never reflect.
• Adds --input-type har to accept HAR exports from Burp, Caido, ZAP, mitmproxy, or DevTools as a scan source.
• Adds --analyze-external-js to fetch and run AST DOM-XSS analysis on a target's same-origin <script src> bundles (capped at 16 files / 512 KiB).

Endpoint Security (EDR/XDR) · 2026-07-06

Fleet v4.88.0 adds support for personal (BYOD) Apple MDM enrollment with per-host wipe/lock permission controls.

• Supports personal (BYOD) Apple MDM enrollment, tracking per-host enrollment permissions to prevent remote wipe or lock of personal devices, with permissions preserved across SCEP/ACME certificate renewal.

Endpoint Security (EDR/XDR) · 2026-07-06

Fleet 4.87.0 adds 963 new managed apps, Android MDM commands, Apple Business rebranding, GCS IAM auth, and a command palette.

• Adds 236 new Fleet-maintained apps for Windows, including Microsoft Office, PowerShell, PowerToys, Power BI, Git, Node.js, Python 3.13/3.14, PostgreSQL 15–18, Nessus Agent, Bitwarden, and more.
• Adds 727 new Fleet-maintained apps for macOS, spanning development, security, productivity, and design tooling.
• Supports issuing Lock, Wipe, and Clear Passcode MDM commands to Android hosts; Wipe is available to Fleet Free users for company-owned Android devices.

Secure Access (VPN / SASE / ZTNA) · 2026-07-06

Headscale v0.29.0 adds SSH check-mode auth, policy tests, grants, Taildrive, nodeAttrs, and HA subnet router health probing.

• New headscale auth CLI command group: approve, reject, and register subcommands manage SSH check-mode and web auth approval flows.
• Supports Tailscale SSH "action": "check" rules, prompting OIDC or CLI approval before granting SSH access to a node.
• Evaluates the tests block in policy files (beta), asserting reachability between sources and destinations; failing tests block writes before they are applied.

Secure Access (VPN / SASE / ZTNA) · 2026-07-06

innernet v2.0.0 adds custom host suffix, client endpoint override, verbose full public keys, and a new innernet-client-core Rust library

• Adds --host-suffix CLI option to client and server to override the default <interface>.wg hostname suffix.
• Adds override-endpoint command to the client, enabling manual peer endpoint specification without going through the server.
• Prints full WireGuard public keys (instead of truncated 10-char versions) when the global --verbose flag is used.

Reconnaissance & OSINT · 2026-07-06

Maigret v0.6.2 adds keyword filtering, Neo4j Cypher export, ORCID support, FlareSolverr bypass, and a threaded DNS fallback.

• Adds --keywords flag to filter results by matching keywords found in profile pages.
• Adds --neo4j flag to export search results as a Neo4j Cypher file for graph database ingestion.
• Adds ORCID as a supported site for academic researcher identity lookups.

Web Application Security · 2026-07-06

v3.11.0 requires digital signatures on all custom JavaScript-protocol templates before Nuclei will load them.

• Breaking change: Custom templates using the javascript: protocol must now be digitally signed; unsigned JavaScript templates are skipped at load time and when referenced from workflows.
• Enforces signature verification for JavaScript templates, extending the code-protocol signing requirement to the JavaScript protocol and its Go-backed runtime modules.

Cloud Security Posture · 2026-07-06

Prowler 5.32.0 adds Kingfisher secret scanning, Azure resource-group scoping, Okta throttling, AWS resource caps, Neptune graph sink, and 6 new checks.

• New secret-scanning engine: replaces detect-secrets with Kingfisher, runs fully offline, suppresses placeholder false positives, and adds --scan-secrets-validate / aws.secrets_validate for live credential verification (confirmed live secrets reported as critical).
• Azure scans now support --azure-resource-group / --azure-resource-groups to scope assessments to one or more resource groups instead of the entire subscription.
• Okta provider adds configurable API request throttling (--okta-requests-per-second, default 4 req/s) and retry cap (--okta-retries-max-attempts, default 5) to survive rate limits on large tenant scans.

Cloud Security Posture · 2026-07-06

Prowler 5.31.0 adds Linode provider, post-quantum AWS checks, DORA coverage for Azure/GCP/Cloudflare/Alibaba, and 30+ new checks across AWS, Azure, GCP, K8s, and M365.

• New linode provider: scans Linode (Akamai Cloud) administration, compute, and networking services via prowler linode.
• New AWS post-quantum cryptography checks: cloudfront_distributions_pqc_tls_enabled, apigateway_domain_name_pqc_tls_enabled, transfer_server_pqc_ssh_kex_enabled, acmpca_certificate_authority_pqc_key_algorithm (new acmpca service), and rolesanywhere_trust_anchor_pqc_pki (new rolesanywhere service).
• New AWS org-wide governance checks: securityhub_delegated_admin_enabled_all_regions and config_delegated_admin_and_org_aggregator_all_regions.

Cloud Security Posture · 2026-07-06

Prowler 5.30 adds full Okta DISA STIG coverage, a universal DORA compliance framework, 8 new checks across AWS/M365/GCP/StackIT, and self-healing background task recovery.

• Adds complete DISA Okta IDaaS STIG V1R2 framework coverage for the Okta provider, spanning six new services: user, authenticator, idp, network, apitoken, and systemlog with 17 new checks covering account inactivity, MFA hardening, password policy, smart card, API token privilege, network zone enforcement, and log streaming.
• Introduces DORA (Digital Operational Resilience Act) as Prowler's first universal compliance framework — defined once and mapped across providers — currently covering AWS checks across the five DORA pillars and exportable in OCSF Compliance Finding format for SIEM ingestion.
• New AWS check sagemaker_models_monitor_enabled verifies each SageMaker monitoring schedule is in the Scheduled state to detect data and model drift.

Reverse Engineering · 2026-07-06

Radare2 6.1.8 adds JWT decoding, new demanglers, type-lookup commands, FTAB/idd/R_DYLDCACHE_NO_DEPS, ESIL stepback, and PPC ESIL coverage.

• Adds pFJ command for JWT token decoding in the print subsystem.
• Adds CLd command for source-baked decompiler output.
• Adds tsn command to look up struct names by size.

Firewalls & Network Defense · 2026-07-06

Rspamd 4.1.1 adds pluggable Neural registries, richer CSS text-hiding detection, zip-bomb limits, and new byte-analysis APIs.

• Adds pluggable feature-provider and ANN-architecture registries to the Neural module, plus a sequence output mode with SIF word selection for fasttext_embed, multi-head attention pooling in kann, and slice/concat graph transforms in lua_kann.
• Enables content-negotiation in checkv3 — representation and compression now negotiated via Accept/Accept-Encoding headers.
• Expands CSS text-hiding detection to cover off-screen positioning, clip, negative text-indent, and tiny fonts.

Secrets Detection & Management · 2026-07-06

Sealed Secrets v0.38.0 adds ppc64le support, default Prometheus alerting rules for out-of-sync secrets, and hardened pod security defaults.

• Adds ppc64le architecture support, enabling Sealed Secrets controller and kubeseal to run on IBM Power (ppc64le) nodes.
• Adds a default PrometheusRule to the Helm chart that alerts when SealedSecrets are out of sync with their unsealed counterparts.
• Updates security context defaults in the Helm chart to comply with the Kubernetes restricted pod security standard profile.

Secrets Detection & Management · 2026-07-06

Helm chart v2.19.0 adds ppc64le support, default Prometheus alerting rules for out-of-sync secrets, and tightened pod security defaults.

• Adds ppc64le architecture support, enabling Sealed Secrets controller deployment on IBM POWER clusters.
• Adds default PrometheusRule to the Helm chart that alerts when SealedSecrets are out of sync with their unsealed counterparts.
• Updates security context defaults to comply with the Kubernetes restricted pod security standard profile.

Vulnerability Management · 2026-07-06

Vuls v0.39.3 switches Windows CVE detection to the vuls2 backend and expands EOL coverage for new OS versions.

• Switches Windows KB-based CVE detection from gost to the vuls2 backend, now reading vuls.db built from microsoft-* sources (breaking change: gost is no longer used for Windows; a vuls.db containing microsoft-* data is required).
• Surfaces MSRC Exploit Status under CveContent.Optional["exploit"] for Windows detections, maintaining parity with the previous gost output.
• Adds EOL data for newly released OS versions via updated GetEOL configuration.

AI Coding Agents · 2026-07-06

• Edits produced in autonomous (Devin Local) mode now generate reviewable diffs instead of silent changes.
• Enforces enterprise login policies in the CLI.

arsenal-ng 1 changes

• v1.5 · Feature · 2026-07-08

bloodhound 1 changes

• v9.4.0 · Feature · 2026-07-09

BunkerWeb 1 changes

• v1.6.12 · Feature · 2026-07-06

Claude Code 5 changes

• v2.1.207 · Feature · 2026-07-11
• v2.1.206 · Feature · 2026-07-10
• v2.1.205 · Feature · 2026-07-09
• v2.1.203 · Feature · 2026-07-09
• v2.1.202 · Feature · 2026-07-08

Cline 4 changes

• v4.0.8 · Feature · 2026-07-11
• v4.0.7 · Feature · 2026-07-09
• cli-v3.0.39 · Feature · 2026-07-09
• cli-v3.0.38 · Feature · 2026-07-08

Cloudflare 6 changes

• Improving Smart Tiered Cache for Public Cloud Regions (2026-07-10) · Feature · 2026-07-11
• docs-20260711-dd1b6cfc · Docs · 2026-07-11
• docs-20260710-d2d7e297 · Docs · 2026-07-10
• docs-20260709-09dd8839 · Docs · 2026-07-09
• Your Worker can now have its own cache in front of it (2026-07-06) · Feature · 2026-07-08
• docs-20260708-4df66ab1 · Docs · 2026-07-08

Cloudsplaining 1 changes

• 0.9.0 · Feature · 2026-07-06

CrewAI 1 changes

• 1.15.2 · Feature · 2026-07-09

Crush 3 changes

• v0.84.0 · Feature · 2026-07-10
• v0.83.0 · Feature · 2026-07-09
• v0.82.0 · Feature · 2026-07-09

CTFd 1 changes

• 3.8.6 · Feature · 2026-07-06

Cursor 2 changes

• Side Chats and Conversation Search · Feature · 2026-07-11
• docs-20260711-93d23ead · Docs · 2026-07-11

Dalfox 2 changes

• v3.1.1 · Feature · 2026-07-06
• v3.1.0 · Feature · 2026-07-06

defectdojo 1 changes

• 3.1.0 · Feature · 2026-07-08

Docker Compose 2 changes

• v5.3.0 · Feature · 2026-07-11
• v5.2.0 · Feature · 2026-07-11

Docker Sandboxes 3 changes

• v0.35.0 · Feature · 2026-07-11
• v0.34.0 · Feature · 2026-07-11
• v0.33.0 · Feature · 2026-07-11

DOMPurify 1 changes

• 3.4.12 · Feature · 2026-07-12

ffuf 1 changes

• v2.2.0 · Feature · 2026-07-12

Fleet 2 changes

• fleet-v4.88.0 · Feature · 2026-07-06
• fleet-v4.87.0 · Feature · 2026-07-06

gemini-cli 1 changes

• v0.50.0 · Feature · 2026-07-09

Headscale 1 changes

• v0.29.0 · Feature · 2026-07-06

httpx-toolkit 1 changes

• v1.10.0 · Feature · 2026-07-10

humble 1 changes

• 1.63 · Feature · 2026-07-09

innernet 1 changes

• v2.0.0 · Feature · 2026-07-06

jadx 1 changes

• v1.5.6 · Feature · 2026-07-11

Kiro 2 changes

• Hooks on Agent Writes, Lazy MCP Auth, and Multi-Window Sync · Feature · 2026-07-10
• Expanded MCP OAuth Support · Feature · 2026-07-10

LangGraph 1 changes

• cli==0.4.31 · Feature · 2026-07-11

LogicGate 2 changes

• GRC Has Entered Its Agentic Era. Here’s What That Means For Your Team. (2026-06-30) · Feature · 2026-07-11
• The Agentic Era, Live: A Recap of Agility 2026 (2026-06-11) · Feature · 2026-07-11

Maigret 1 changes

• v0.6.2 · Feature · 2026-07-06

Microsoft Security 1 changes

• docs-20260708-b0805b16 · Docs · 2026-07-08

Microsoft Sysinternals 1 changes

• LiveKd v5.65, ProcDump v12.01, and ZoomIt v12.11 (2026-07-09) · Feature · 2026-07-11

nuclei 1 changes

• v3.11.0 · Feature · 2026-07-06

Ollama 1 changes

• v0.31.2 · Feature · 2026-07-09

OpenAI Codex CLI 6 changes

• rust-v0.144.0 · Feature · 2026-07-10
• rust-v0.144.0-alpha.4 · Feature · 2026-07-09
• rust-v0.143.0 · Feature · 2026-07-09
• rust-v0.144.0-alpha.2 · Feature · 2026-07-09
• rust-v0.144.0-alpha.1 · Feature · 2026-07-09
• rust-v0.143.0-alpha.39 · Feature · 2026-07-09

OpenCode 4 changes

• v1.17.18 · Feature · 2026-07-10
• v1.17.17 · Feature · 2026-07-10
• v1.17.16 · Feature · 2026-07-09
• v1.17.14 · Feature · 2026-07-08

OpenHands 10 changes

• cloud-1.46.0 · Feature · 2026-07-11
• 1.11.0 · Feature · 2026-07-10
• cloud-1.45.0 · Feature · 2026-07-10
• cloud-1.44.0 · Feature · 2026-07-10
• 1.10.0 · Feature · 2026-07-09
• cloud-1.43.0 · Feature · 2026-07-09
• 1.9.1 · Feature · 2026-07-09
• cloud-1.42.0 · Feature · 2026-07-09
• 1.9.0 · Feature · 2026-07-08
• cloud-1.41.0 · Feature · 2026-07-08

Palo Alto Prisma Cloud 1 changes

• changelog · Jul 7, 2026 · Feature · 2026-07-09

Pi 7 changes

• v0.80.6 · Feature · 2026-07-11
• v0.80.3 · Feature · 2026-07-11
• v0.80.0 · Feature · 2026-07-11
• v0.79.10 · Feature · 2026-07-11
• v0.79.9 · Feature · 2026-07-11
• v0.79.8 · Feature · 2026-07-11
• v0.79.7 · Feature · 2026-07-11

Prowler 4 changes

• 5.33.0 · Feature · 2026-07-08
• 5.32.0 · Feature · 2026-07-06
• 5.31.0 · Feature · 2026-07-06
• 5.30.0 · Feature · 2026-07-06

Qualys CyberSecurity Asset Management 1 changes

• changelog · Jul 7, 2026 · Feature · 2026-07-09

Qualys Patch Management 1 changes

• changelog · Jul 8, 2026 · Feature · 2026-07-09

Radare2 1 changes

• 6.1.8 · Feature · 2026-07-06

Rapid7 Insight Platform 1 changes

• Cloud Security (InsightCloudSec) Release Notes (2026-07-07) · Feature · 2026-07-08

Rapid7 InsightCloudSec 1 changes

• changelog · Jul 9, 2026 · Feature · 2026-07-10

Rspamd 1 changes

• 4.1.1 · Feature · 2026-07-06

Sealed Secrets 2 changes

• v0.38.0 · Feature · 2026-07-06
• helm-v2.19.0 · Feature · 2026-07-06

Sigma Rules 1 changes

• r2026-07-01 · Feature · 2026-07-10

sigma-cli 1 changes

• v3.1.0 · Feature · 2026-07-09

Snyk Container 1 changes

• changelog · Jul 10, 2026 · Docs · 2026-07-10

spire 1 changes

• v1.15.2 · Feature · 2026-07-10

Stratus Red Team 1 changes

• v2.34.0 · Feature · 2026-07-11

trufflehog 1 changes

• v3.95.9 · Feature · 2026-07-10

Vanta 1 changes

• June 2026 · Feature · 2026-07-11

Vuls 1 changes

• v0.39.3 · Feature · 2026-07-06

Windsurf 4 changes

• updated · Jul 11, 2026 · Feature · 2026-07-11
• updated · Jul 10, 2026 · Feature · 2026-07-10
• updated · Jul 7, 2026 · Feature · 2026-07-08
• updated · Jul 6, 2026 · Feature · 2026-07-06

Wiz Cloud 1 changes

• changelog · Jul 8, 2026 · Feature · 2026-07-09

Wiz Defend 1 changes

• changelog · Jul 8, 2026 · Feature · 2026-07-09

xsrfprobe 1 changes

• v3.0.0 · Feature · 2026-07-12

Zscaler Data Protection 1 changes

• changelog · Jul 8, 2026 · Feature · 2026-07-09

Zscaler Posture Control 1 changes

• changelog · Jun 26, 2026 · Feature · 2026-07-09

Claude Code v2.1.207 · 2026-07-11

Auto mode no longer reads autoMode from .claude/settings.local.json (repo-resident); use ~/.claude/settings.json instead

Claude Code v2.1.207 · 2026-07-11

${user_config.*} in shell-form commands for plugin hooks/monitors/MCP headersHelper is now rejected; hooks must use exec form (args array) or $CLAUDE_PLUGIN_OPTION_<KEY>; monitors and headersHelper must read the value inside the script

Claude Code v2.1.207 · 2026-07-11

Plugin option values (pluginConfigs) are no longer read from project-level .claude/settings.json; only user, --settings, and managed settings are honored

Docker Sandboxes v0.35.0 · 2026-07-11

Host env vars no longer auto-inject at runtime — use sbx secret import to migrate existing env-var-based secrets.

Docker Sandboxes v0.35.0 · 2026-07-11

sbx rm now won't delete an active session unless --force is passed.

Docker Sandboxes v0.35.0 · 2026-07-11

Installation is blocked on Windows versions older than Windows 11.

Docker Sandboxes v0.34.0 · 2026-07-11

Kit installs are restricted to an allowlist of sources defaulting to Docker Hub (docker.io/) only; installing a kit from another registry or a Git URL fails until you add its prefix with sbx settings set kit.allowedSources.

Docker Sandboxes v0.34.0 · 2026-07-11

The sbx policy set-default command is renamed to sbx policy init (the old name still works as a hidden deprecated alias, but is deprecated).

Docker Sandboxes v0.33.0 · 2026-07-11

The sbx run <name> positional argument form for re-attaching to an existing sandbox now prints a deprecation warning; the positional argument for sbx run is expected to be an agent (e.g. claude, codex), not a sandbox name, and the old positional-name form will be removed in a future release.

Docker Sandboxes v0.33.0 · 2026-07-11

sbx run --name no longer auto-creates numbered sibling sandboxes when a same-named sandbox exists.

Docker Sandboxes v0.33.0 · 2026-07-11

sbx create now errors when run without arguments instead of proceeding.

Pi v0.80.3 · 2026-07-11

The default OpenAI model is changed to gpt-5.5.

Pi v0.80.0 · 2026-07-11

The @earendil-works/pi-ai/base and @earendil-works/pi-agent-core/base entrypoints have been removed; use the root packages with explicit Models provider factories instead.

Pi v0.80.0 · 2026-07-11

The global API (stream/complete/completeSimple, getModel/getModels/getProviders, registerApiProvider, getEnvApiKey, etc.) has been moved off the @earendil-works/pi-ai root entrypoint to @earendil-works/pi-ai/compat; extension sources that typecheck against pi-ai's published types must switch those imports to @earendil-works/pi-ai/compat or migrate to the new createModels()/provider-factory API.

Pi v0.79.7 · 2026-07-11

The pi update command now updates only pi itself; the previous behaviour of updating pi and packages together now requires pi update --all.

Claude Code v2.1.205 · 2026-07-09

User-configured MCP servers can no longer register under the names Claude Browser or Claude Preview

Claude Code v2.1.203 · 2026-07-09

The left arrow key no longer closes the background tasks, diff, and workflow detail views — press Esc instead

sigma-cli v3.1.0 · 2026-07-09

Python 3.9 is no longer supported

Cloudsplaining 0.9.0 · 2026-07-06

Python 3.9 is no longer supported

Cloudsplaining 0.9.0 · 2026-07-06

Node 18 and Node 22 are no longer supported

Headscale v0.29.0 · 2026-07-06

MagicDNS GivenName collision suffix changed from 8-char random hash (laptop-abc12xyz) to monotonic numeric suffix (laptop, laptop-1, laptop-2, …); MagicDNS names change on upgrade for any node whose previous label was a random-suffix form

Headscale v0.29.0 · 2026-07-06

Empty or all-non-ASCII hostnames now fall back to the literal node instead of invalid-<rand>

Headscale v0.29.0 · 2026-07-06

Wildcard (*) in ACL sources and destinations now resolves to the Tailscale CGNAT range (100.64.0.0/10) and ULA range (fd7a:115c:a1e0::/48) instead of all IPs (0.0.0.0/0 and ::/0); policies relying on * to match all IP addresses must switch to autogroup:danger-all (source only) or explicit CIDR ranges (destinations)

Headscale v0.29.0 · 2026-07-06

Policies using tags, hosts, or IP addresses as sources for autogroup:self destinations now fail validation

Headscale v0.29.0 · 2026-07-06

proto:icmp now only includes ICMPv4 (protocol 1); ICMPv6 must be specified explicitly as proto:ipv6-icmp or protocol number 58

Headscale v0.29.0 · 2026-07-06

Skipping minor versions (e.g. 0.27 → 0.29) is blocked; upgrades must proceed one minor version at a time, and downgrading to a previous minor version is blocked

Headscale v0.29.0 · 2026-07-06

The randomize_client_port server-config key was removed; headscale refuses to start when the old key is present — the toggle must be moved to the policy file as the top-level randomizeClientPort field

Headscale v0.29.0 · 2026-07-06

Minimum supported Tailscale client version is now v1.80.0

innernet v2.0.0 · 2026-07-06

The Rust libraries innernet-client-core, innernet-server, and innernet-shared have semver-incompatible API changes requiring a major version bump for consumers of these crates

nuclei v3.11.0 · 2026-07-06

Custom templates that use the javascript: protocol must be digitally signed before Nuclei will load or execute them; unsigned JavaScript templates are skipped during template loading and when referenced from workflows.

Prowler 5.32.0 · 2026-07-06

The detect_secrets_plugins configuration option has been removed, as it is no longer used by the new secret-scanning engine (Kingfisher).

Radare2 6.1.8 · 2026-07-06

The sdb_remove function has been deprecated as a duplicate of sdb_unset

Radare2 6.1.8 · 2026-07-06

The asm.addr.base10 and asm.addr.base36 config keys are unified into asm.addr.base

Radare2 6.1.8 · 2026-07-06

The esil.verbose config key has been removed

Radare2 6.1.8 · 2026-07-06

The default CPU for AVR is now ATxmega128a4u

Radare2 6.1.8 · 2026-07-06

The iz+ command now requires spaced arguments