grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, obfuscation, or unauthorized access patterns were detected. The prompt is strictly instructional and focused on design review workflows.
- [DATA_EXPOSURE]: The skill uses codebase exploration to resolve design dependencies. This is a standard functional requirement for a developer assistant and does not involve unauthorized access to sensitive system files, environment variables, or credentials.
- [PROMPT_INJECTION]: The skill reads codebase content, which presents an indirect prompt injection surface (Category 8). Ingestion point: Codebase files. Boundary markers: Absent. Capability inventory: File read access. Sanitization: Absent. The risk is considered safe as the agent's output is limited to interviewing the user within a controlled design-review context.
Audit Metadata