behavioral-modes
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No security issues detected. The skill provides behavioral guidelines for an AI agent without introducing malicious logic.
- Tooling & Permissions (SAFE): The skill is limited to 'Read', 'Glob', and 'Grep' tools, which are restricted to local file access for reading only. It does not request shell execution or network access.
- Indirect Prompt Injection (SAFE): While the skill processes external data in 'REVIEW' and 'DEBUG' modes, it does not use unsafe interpolation or possess capabilities to exfiltrate data or execute code from those files.
Audit Metadata