Provides secure, read-only filesystem access for AI applications. Features directory operations with recursive traversal, search capabilities including file globbing and regex content searching, file reading with head/tail support, and comprehensive analysis tools for directory statistics and metadata. Includes symlink escape protection, path traversal prevention, and access control for explicitly allowed directories only.
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.