explore-app-store

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text via the model-provided --terms into iTunes Search queries and consumes response fields like app description (and screenshots URLs) from first-party APIs at runtime (e.g., scripts/explore.py sweep → scripts/appstore.py itunes_search → norm_itunes stores description and extract_prices parses it).