xy-course

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads user-authored files, check-in answers, and feedback text from the local course directory, which constitutes ingestion of user-supplied/outsider text into the runtime path.

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

• Potentially malicious external URL detected (high risk: 0.70). The script connects to api.xyskill.xyz at runtime via HTTP POST to query search data, constituting an unverifiable runtime external dependency under weak/unknown provenance.