grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to explore the codebase to resolve questions about a design or plan, which presents an inherent surface for indirect prompt injection if malicious instructions are present in the files being read.
- Ingestion points: Local codebase files accessed during the 'explore the codebase' instruction (SKILL.md).
- Boundary markers: None specified in the instructions to separate data from instructions.
- Capability inventory: Relies on the agent's default file system exploration and reading tools.
- Sanitization: No specific sanitization or filtering of codebase content is mentioned.
Audit Metadata