grill-me
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill's instructions are limited to conducting a conversational interview and do not include any malicious patterns such as prompt injection, data exfiltration, or obfuscation.- [COMMAND_EXECUTION]: The skill directs the agent to explore the local codebase to answer questions when applicable. This is a routine operation for development-oriented agents and does not pose a security risk in this context.
Audit Metadata