grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a specialized conversational role for stress-testing project designs and plans. No malicious commands, obfuscation, or data exfiltration attempts were found.
- [PROMPT_INJECTION]: The skill directs the agent to explore the codebase to answer questions. While this constitutes a surface for indirect prompt injection from codebase content, it is a routine functionality for development-oriented agents.
- Ingestion points: Local codebase files (referenced in SKILL.md).
- Boundary markers: None specified.
- Capability inventory: Read-only access to the project codebase.
- Sanitization: No specific input sanitization is defined for codebase content.
Audit Metadata