red-team-my-app

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to perform a static risk review of application artifacts such as PRDs and architecture plans.
  • [SAFE]: File system operations are restricted to reading and writing documentation within the docs/ai-native/ directory.
  • [SAFE]: The skill contains no network operations, external downloads, or execution of untrusted code.
  • [SAFE]: The 'Source Loading Protocol' ensures the agent relies on local project files rather than external or potentially malicious inputs for its analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 04:18 AM
Security Audit — agent-trust-hub — red-team-my-app