grill-me
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of natural language instructions to modify the agent's conversational persona. No malicious patterns such as prompt injection, data exfiltration, or unauthorized code execution were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided plans. While it utilizes the agent's ability to explore the codebase to answer questions, there is no evidence of unsafe interpolation or high-risk capability exposure beyond the intended use case.
Audit Metadata