safety-guard
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely descriptive and documentation-focused, outlining a system to monitor and intercept potentially destructive shell commands such as 'rm -rf' and 'git push --force'.
- [SAFE]: There are no indicators of data exfiltration or credential harvesting; the mentioned logging path '~/.claude/safety-guard.log' is a local file for auditing blocked actions.
- [SAFE]: The skill does not include any executable code, scripts, or external dependencies that could introduce security vulnerabilities.
Audit Metadata