analyst

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

• Third-party content exposure detected (high risk: 0.70). The skill's templates and workflows (e.g., the "Monitoring & Intelligence Plan" intelligence-sources and multiple sections in the market-research and competitor-analysis templates) explicitly instruct gathering and using public third-party content such as company websites/blogs, customer reviews, industry reports, and social media—untrusted user-generated sources—which the agent is expected to read and use to produce recommendations that can change subsequent actions.