grill-me
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are focused on providing a structured interview process for design review. No malicious code, prompt injection, or data exfiltration patterns were found. The skill uses standard reasoning and codebase exploration to fulfill its stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to explore the codebase to resolve questions. This represents a potential surface for indirect prompt injection if malicious instructions are embedded in the codebase being analyzed. However, this is an inherent aspect of codebase analysis tools and does not involve unsafe capabilities like code execution or network exfiltration.
- Ingestion points: The local codebase being analyzed.
- Boundary markers: None present.
- Capability inventory: Codebase exploration (file read).
- Sanitization: None present.
Audit Metadata