competitor-analyst

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

• Third-party content exposure detected (high risk: 0.90). The skill's Advanced Patterns explicitly tell the agent to "read their marketing page, then read their support forums and app store reviews," which requires fetching and interpreting untrusted public/user-generated content (marketing pages, support forums, app-store reviews) that can influence analysis and next actions.