client-discovery

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 "Research — Parallel Market Intelligence" explicitly instructs Agent 1 to gather and interpret customer content from reviews, forums, and social media ("What are customers saying in reviews, forums, social media? ... Return structured findings with sources"), which is untrusted third-party user-generated content that will be read and used to drive subsequent synthesis and recommendations.