grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided plans and designs as its primary input, which represents an ingestion point for untrusted data. It also utilizes codebase exploration capabilities to resolve questions. This combination creates an indirect prompt injection surface.
- Ingestion points: User-provided plans or designs (SKILL.md).
- Boundary markers: Absent; the instructions do not define specific delimiters for the plan data.
- Capability inventory: Codebase exploration via file read tools.
- Sanitization: Absent; the skill does not define specific sanitization or validation for the processed data.
Audit Metadata