safety-guard
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a monitoring system that intercepts potentially destructive shell command patterns, such as recursive deletions (rm -rf), forced git pushes, and database deletions, providing a safety buffer for autonomous operations.- [SAFE]: The skill includes a directory-locking feature that restricts file modifications to user-defined paths, preventing the agent from making unintended changes outside the designated scope.- [SAFE]: The skill logs blocked operations to a local file path (~/.claude/safety-guard.log) for user audit and transparency.- [SAFE]: No remote dependencies, external network calls, or obfuscated content were detected within the skill instructions.
Audit Metadata