skills/nirabo/skills/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable code or external dependencies; it consists entirely of behavioral prompts for a design-review persona. No malicious patterns or bypass attempts were detected.
  • [PROMPT_INJECTION]: The skill involves analyzing user-provided plans (an indirect ingestion point). However, the agent's instructions focus on critical inquiry and codebase exploration rather than executing untrusted commands. No risk of behavior override was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 11:53 AM