grill-me

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions intended to guide agent behavior during a design review. No malicious code, obfuscation, or unauthorized network operations were detected.- [INDIRECT_PROMPT_INJECTION]: The skill includes an instruction to explore the codebase if a question can be answered there. This identifies the local codebase as an ingestion point for external data. However, this is a standard capability for developer-oriented agents and lacks any specific indicators of malicious intent or safety bypasses. (File: SKILL.md)
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 04:25 AM
Security Audit — agent-trust-hub — grill-me