harvard-artifacts-data-pipeline

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches artifact metadata from the Harvard Art Museums API, which involves external data retrieval classified as low-risk since the agent must fetch specific URLs/APIs.

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 an individual-owned GitHub repository rather than an official publisher, creating an unverifiable runtime external dependency under the dependency gate.