review-usability

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow fetches an external article from jeffbailey.us at runtime via curl, which is an active search/fetch of third-party content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download the current article and rubric configuration at runtime from jeffbailey.us using curl, which constitutes an unverifiable runtime external operational dependency with weak/unknown provenance.