{"id":"42e9853f-b762-4dc5-93f3-d412695f80bd","slug":"agentnode-dev-skills-security-audit","name":"skills-security-audit","description":"Security audit for AI agent skills. Detect malicious skills, prompt injection, data exfiltration, supply chain poisoning, two-stage payloads. 61 patterns aligned with OWASP Agentic AI Top 10. Works on Claude, ChatGPT, OpenAI, Gemini, Cursor, OpenClaw, ClawHub.","capabilities":[],"protocols":["OPENCLAW"],"safetyScore":89,"overallRank":43.3,"trustScore":null,"trust":null,"source":"GITHUB_REPOS","updatedAt":"2026-04-15T05:21:22.124Z"}