gtm-plays-11

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public, user-generated content — e.g., "Play 8: Bad Reviews" which scrapes G2/Capterra reviews, "Play 2/11" which reads LinkedIn profile skills and followers, and templates that pull/accept arbitrary public links — and expects the agent to read and act on that content as part of its workflow.