security-best-practices
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, exfiltration attempts, or obfuscated content were detected across the skill files.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external codebases which may contain malicious instructions. To mitigate this risk, the skill includes explicit anti-patterns that forbid treating external content or tool responses as trusted instructions, and a verification protocol to ensure results are based on local evidence.
Audit Metadata