A deliberately narrow, approval-gated workspace server that safely reads and writes files and runs allowlisted commands only inside one configured workspace, requiring visible approval for every write, process execution, and file read, with stale-overwrite protection and symlink-escape rejection.
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 2026-08-29.
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.