safety-guard
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill serves as a protective layer that monitors agent actions for destructive patterns such as recursive deletions, forceful git operations, and administrative permission changes.
- [COMMAND_EXECUTION]: It employs a hook mechanism to run a local script (node hooks/scripts/safety-guard.js) which evaluates tool calls before execution to ensure they comply with established safety modes.
Audit Metadata