Provides deep repository analysis through tree-sitter parsing, call graph generation, and security vulnerability scanning across 16 programming languages. Features incremental indexing, neural embeddings for semantic code search, taint analysis for tracking data flow vulnerabilities, SBOM generation, and dependency auditing with OWASP/CWE coverage.
Cognium trust score
66%
Tier
Scanned
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 2026-09-28.
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.