grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized network activity was detected. The instructions are focused on legitimate design review tasks.
- [PROMPT_INJECTION]: The skill enables the agent to explore the codebase to answer questions. This constitutes an indirect prompt injection surface as the agent ingests data from files. However, this is a standard capability for developer-oriented agents and does not involve malicious intent within the skill itself. No specific delimiters or sanitization instructions for codebase content are provided.
Audit Metadata