localization

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

• Third-party content exposure detected (high risk: 0.80). The skill's required "Phase 1: Research" steps explicitly tell the agent to "Analyze top 10 apps in your category" and to check local competitors' metadata and local autocomplete/keyword suggestions from App Store markets — actions that require fetching and interpreting public third‑party App Store content (untrusted developer/user-generated listings) that could influence subsequent recommendations.