grill-me
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a benign interview persona for design review. No malicious code, exfiltration, or persistence patterns were detected.
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by instructing the agent to explore the codebase to answer questions.
- Ingestion points: codebase (SKILL.md)
- Boundary markers: absent
- Capability inventory: file reading
- Sanitization: absent
Audit Metadata