ask-what-breaks

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill provides logical instructions for the AI to perform a 'red teaming' task on claims. No harmful instructions, obfuscated code, or unauthorized data access patterns are present.
  • [EXTERNAL_DOWNLOADS]: The README provides links to the author's GitHub repository for installation purposes. This is a standard distribution method for the platform and originates from the skill's official source.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 05:24 PM
Security Audit — agent-trust-hub — ask-what-breaks