content-management

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No prompt injection patterns were detected. The skill's instructions are purely functional and oriented toward content management tasks without attempting to override safety guidelines.
  • [SAFE]: Data handling is documented with a strong focus on security. The 'SECURITY.md' file includes detailed protocols for XSS prevention, SVG sanitization, and file upload validation.
  • [SAFE]: Command execution is limited to local Node.js test scripts used to validate the skill's structure and agents. These scripts do not process untrusted external input.
  • [SAFE]: The skill documentation includes comprehensive guidelines for API key management and secret storage, emphasizing the use of environment variables and rotation rather than hardcoding credentials.
  • [SAFE]: Indirect prompt injection surfaces exist due to the processing of user-provided briefs and external content, but the skill explicitly addresses this risk through mandatory sanitization and validation workflows outlined in the operations and security guides.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 12:17 AM