harvard-art-museum-etl-pipeline

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

• Third-party content exposure detected (high risk: 0.85). The runtime workflow fetches free-form JSON fields (e.g., artifact titles, descriptions, URLs, image metadata) from the Harvard Art Museums API via requests.get(...).json() in fetch_artifacts()/extract_all_artifacts(), and those values are then converted into LLM-readable text fields (e.g., title, culture, period, etc.) in transform_artifacts() and used downstream; this is outsider-authored public web/API content.