Provides terminal command execution, filesystem operations, and system process monitoring through a configurable security model. Supports command allowlisting and blocklisting, timeout controls, and output size limits. Includes tools for running shell commands, reading and writing files, listing directories, checking file existence, and inspecting running processes and environment variables.
Cognium trust score
92%
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 2026-09-19.
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.