market-research

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to "use web search when available to gather current information" and to assess "what are users complaining about," which requires fetching and interpreting open/public third-party content (product websites, reviews, forums/social media) that could contain untrusted user-generated input.