harvard-art-museums-etl-analytics

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches artifact data and descriptions from the Harvard Art Museums API, which contains third-party museum records and descriptions, representing an indirect prompt injection risk via API data ingestion.

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

• Potentially malicious external URL detected (medium risk: 0.30). The repository clone URL references personal/unofficial third-party code that is retrieved and installed during setup, constituting an unverifiable operational dependency.