First reported github.com
Tools · latest
First reported github.com
GitHub - NVIDIA/SkillSpector: Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
NVIDIA's SkillSpector is an open-source security scanner that inspects AI agent skills for vulnerabilities, malicious patterns, prompt injection, data exfiltration, and supply-chain risks before installation, supporting Claude Code, Codex, and MCP skills. The GitHub repository is publicly available with ongoing commits and releases. Details →First reported medium.com
Block AI from installing malicious npm packages
Prasanna Mestha describes a defensive tool built to sit between AI coding agents and the npm registry to block installation of malicious or hallucinated packages, framed around the slopsquatting threat. The write-up cites real cases including the phantom 'react-codeshift' package requested hundreds of times a day and an August campaign in which a single threat actor pushed over 700 AI-named malicious npm packages that deliver a cross-platform RAT via README instructions. Details →First reported · updated · 3 reports github.com
GitHub - sattyamjjain/agent-audit-kit: Static scanner for MCP-connected AI agent pipelines. 296 rules across 12 categories, 12 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.
agent-audit-kit is a static scanner for MCP-connected AI agent pipelines, shipping 296 rules across 12 categories, mappings to 12 compliance frameworks, OWASP Agentic 10/10 and MCP 10/10 coverage, a GitHub Action, SARIF output, and a public CVE-to-rule ledger. The tool is aimed at helping defenders detect security weaknesses in AI agent and MCP integrations before deployment. Details →First reported github.com
GitHub - ytkoka/mcp-tester: A web-based tool for inspecting MCP servers. Connect to any MCP server, browse its Tools, Resources, and Prompts, measure fetch latency, estimate token usage, score the quality of tool definitions, and compare two servers side by side, and scan for tool poisoning and rug pulls.
mcp-tester is an open-source web-based tool by ytkoka for inspecting MCP (Model Context Protocol) servers: it connects to any MCP server, browses Tools, Resources, and Prompts, measures fetch latency, estimates token usage, scores tool-definition quality, compares two servers, and scans for tool poisoning and rug pulls. The repository is published on GitHub under an MIT license with a live demo. Details →First reported · updated · 2 reports howtoharden.com
Cursor Hardening Guide | How to Harden
The How to Harden Cursor guide provides a set of runnable hardening scripts (published in the grcengineering/how-to-harden GitHub repo) to secure the Cursor agentic coding IDE, covering privacy mode, .cursorignore templates, API key rotation, MCP server auditing, agent settings, rules-file auditing, workspace trust, extension auditing, telemetry, and network allowlisting. The guidance references known Cursor risks such as prompt injection, over-permissioned agent actions, and MCP-related CVEs (e.g., CVE-2025-54135/CurXecute and CVE-2025-54136/MCPoison). Details →First reported github.com
GitHub - MauricioPerera/mcpwasm: Static MCP: your tools are files, not servers. Hash-verified static skills executed sandboxed on demand (QuickJS-wasm on Cloudflare Workers) + llms.txt gateway
mcpwasm is a project that reimagines MCP tools as static, hash-verified files rather than running servers, executing each "skill" sandboxed on demand via QuickJS-wasm on Cloudflare Workers, with an llms.txt gateway. Skills declare sha256 hashes and the gateway re-verifies content on every read, rejecting tampered or drifted tool code (including a deliberate corrupt_skill fixture that tests hash-based rejection). Details →First reported github.com
GitHub - prompt-security/clawsec: A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
clawsec, published by prompt-security on GitHub, is an installable security skill suite for AI coding agents (referred to as OpenClaw, Hermes, PicoClaw and NanoClaw) that provides drift detection, live security recommendations, automated audits, and skill integrity verification for agent configuration files such as SOUL.md. The repository includes automated NVD/GHSA advisory syncing and packaged, npx-installable skills for hardening agent setups. Details →First reported arxiv.org
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
Tencent's Zhuque Lab released AI-Infra-Guard, an open-source multi-layer AI agent red-teaming framework, on June 30, 2026, described in an arXiv paper and published to GitHub. The framework matches a detection paradigm to each layer of an agent's attack surface: deterministic rule matching over 75+ components and 1,400+ vulnerability rules, LLM-driven agentic auditing of MCP servers and agent-skill packages (supply-chain auditing), multi-turn black-box agent red teaming, and a jailbreak harness with 26+ attack operators across sixteen datasets. Details →First reported sauleau.com
Sven Sauleau: Systems Engineer - airgap - Security for the modern AI age
airgap is a Linux-only Rust tool (installable via `cargo install airgap`) that runs AI agents like claude/opencode and package managers like npm inside mount/user namespaces with a FUSE filesystem, redacting secrets in files (.env, SSH/PGP keys, .npmrc) and gating unexpected file access. It is positioned to prevent secret exfiltration by AI agents and malicious npm packages such as the Shai-Hulud worm. Details →First reported freyzo.github.io
deep-xpia - multi-hop cross-prompt injection benchmark
deep-xpia is a benchmark of multi-hop cross-prompt injection (DXPIA) across delegated agent boundaries, with 300 live-measured cases and 8 attack patterns showing 69% land undefended and 12% even with all defenses. It highlights registry injection at tool-discovery (DXPIA-008) entering upstream of all 5 stacked defenses and maps patterns to documented Copilot incidents like EchoLeak. Details →First reported github.com
GitHub - denoland/clawpatrol: Security firewall for agents
Clawpatrol is an open-source security firewall for AI agents from denoland, designed to sandbox external plugins (treated as an untrusted supply-chain attack surface) using OS-level namespaces, Landlock, and macOS sandbox profiles, with permission lockfiles and brokered network dialing. Details →How the wire is made
Poll & cluster
Internet is crawled for AI security news and near-duplicate coverage is embedded and grouped into durable items.
Curate
AI Agent filters for agentic-AI relevance, classifies and tags each item, scores severity for threats, and writes the summary.
Every item here is one machine-curated intelligence object, not a headline.
Read the wire for free. There is a small charge to ask the index questions.
The wire, open
The complete curated feed, no key required.
- GET /feed.xml — RSS 2.0, every item
- GET /api/items — read-only
The vector desk
Query the index by meaning, not just keyword.
- GET /api/items?tags=&minSeverity=&itemType=
- GET /api/search?q= — keyword
- GET /api/semantic?q= — vector