Enables direct control of the host operating system through command execution, filesystem operations, and system information retrieval. Each tool can be individually enabled or disabled, and all tool calls support user approval prompts via native system dialogs (notify-send, kdialog, zenity) to prevent unintended operations. Supports custom tool definitions and runs as stdio, SSE, or streamable HTTP server.
Cognium trust score
80%
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.