grill-me-mateo

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions guiding the agent on how to interview a user about code design. It contains no executable code or scripts.
  • [SAFE]: No network operations, external downloads, or exfiltration patterns were detected. All URL references are internal file paths within a repository structure.
  • [SAFE]: The references to 'mateonunez.co' and 'setup-mateonunez-skills' are consistent with the skill author's identity and represent legitimate development contexts.
  • [SAFE]: While the skill processes user-supplied plans (Indirect Prompt Injection surface), its only instructed action is to ask architectural questions, which is a benign capability.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 04:02 PM
Security Audit — agent-trust-hub — grill-me-mateo