ask-design-questions

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a local file (.adits/questions.json) as a temporary transport mechanism to facilitate user communication through structured forms, which is a legitimate and safe workflow.
  • [SAFE]: No unauthorized file access, credential harvesting, or network-based exfiltration attempts were identified.
  • [SAFE]: The instructions are focused entirely on design clarification and do not attempt to bypass agent safety filters or override system behavior maliciously.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 01:06 AM
Security Audit — agent-trust-hub — ask-design-questions