Offers AI assistants secure, sandboxed terminal access with built-in risk analysis for all commands. Uses a deny-by-default security model with 14 MCP tools covering command execution, file operations, and process management. Designed to prevent accidental or malicious system damage when AI agents run terminal commands. Published as an npm package.
Cognium trust score
63%
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 2026-09-01.
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.