p-grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown instructions and YAML configuration. No scripts (Python, JavaScript, shell) or binary executables are included, eliminating risks associated with code execution or privilege escalation.
- [PROMPT_INJECTION]: No evidence of jailbreak attempts, safety filter bypasses, or instruction-override patterns. The skill defines specific trigger conditions and emphasizes that implementation should not occur without explicit user confirmation.
- [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive local file paths (e.g., SSH keys, environment variables) were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided plans and designs, which is a potential injection surface. However, the skill's primary function is to generate questions and decision trees for the user to review, and it lacks automated write or network capabilities that would make such an injection exploitable. All critical decisions require a human-in-the-loop confirmation step.
Audit Metadata