safety-guard
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill serves as a protective layer, instructing the agent to monitor its own tool usage and block potentially destructive commands like 'rm -rf' or 'git push --force'.
- [SAFE]: No external network requests, remote script downloads, or unauthorized data exfiltration patterns were detected. The mentioned logging to '~/.claude/safety-guard.log' is a standard auditing practice.
- [NO_CODE]: The skill consists entirely of markdown instructions and documentation without including any executable scripts, binaries, or configuration files that could hide malicious logic.
- [SAFE]: No obfuscation techniques, hidden URLs, or attempts to bypass safety filters were found within the instructions.
Audit Metadata