Gates all skill installations behind comprehensive threat detection, scanning GitHub repositories against 60+ threat patterns across categories including prompt injection, reverse shells, credential theft, supply chain attacks, and cryptocurrency mining. Critical threats are permanently blocked while medium/high risk installations require explicit force override. Provides search and AI-powered discovery of skills from the SkillsMP marketplace, cloud sync capabilities, and compatibility across multiple MCP clients including Claude Code, OpenClaw, Cursor, Windsurf, GitHub Copilot, Zed, and nanobot.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.