Analyzes GitHub repositories for security risks with four scanning tools: secret detection in commit history via TruffleHog, CVE vulnerability scanning of dependencies via Trivy, high-churn hotspot file identification from git history, and full dependency inventory extraction from package manifests. Designed for reliable agent integration with standardized response structures.
Cognium trust score
98%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-19.
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.