grill-me
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides behavioral instructions to facilitate a shared understanding of designs through persistent questioning. No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were found in the instructions or metadata.
- [COMMAND_EXECUTION]: The instruction to 'explore the codebase' refers to the agent's standard capability to read local files to inform its responses. This is a legitimate use of project context for its stated purpose of design review.
Audit Metadata