find-skills
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a 'Strict Local-Only Policy', explicitly prohibiting network calls, remote registry access, and automatic installations.\n- [COMMAND_EXECUTION]: The skill uses filesystem tools (Glob) to inventory local files in standard agent directories (e.g., ~/.claude/skills/). It explicitly instructs the agent to avoid shell-based search tools like find or grep to prevent command injection or unintended execution.\n- [PROMPT_INJECTION]: The skill includes instructions to ignore potentially malicious commands from other skills and requires explicit user consent before performing any manual installation steps.
Audit Metadata