grill
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to 'Explore context' by reading files, documentation, and recent commits within the repository. Maliciously crafted data within these sources could attempt to influence the agent's recommendations or design outcomes. However, the risk is categorized as low because the skill explicitly prohibits code implementation until a human-confirmed design phase is complete, and it does not possess autonomous execution capabilities.
Audit Metadata