review-analysis

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to call get_app_reviews (via AppKittie's review data) to fetch App Store/Google Play user reviews—public, user-generated content—which the agent must read and analyze to drive decisions and recommendations, creating a clear vector for indirect prompt injection.