grill-me
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is limited to conversational interviewing and reading local documentation (e.g., Architecture Decision Records) to provide context for design reviews. It does not implement or invoke any dangerous tools.
- [SAFE]: No commands for file writing, network exfiltration, or external code execution are present. The instructions explicitly tell the agent to output text for the user to copy rather than writing to disk.
- [SAFE]: Metadata and repository links point to the author's legitimate GitHub infrastructure with no evidence of obfuscation, typosquatting, or impersonation.
Audit Metadata