grilling
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill's instructions are focused on a structured design review process involving interviewing the user and inspecting the codebase.
- [PROMPT_INJECTION]: The skill does not contain instructions to override agent safety guidelines or bypass system prompts.
- [DATA_EXFILTRATION]: No patterns of data exfiltration, sensitive file access, or network operations were found.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands, scripts, or privilege escalation attempts. The instruction to 'explore the codebase' relies on the agent's standard, safe toolset.
Audit Metadata