competitor-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow calls search_apps and get_app_detail to fetch public app-store listings (titles, descriptions, ratings/reviews, ad creative) — untrusted, user-generated/public content the agent is expected to read and use to drive analyses and recommendations, creating a clear avenue for indirect prompt injection.