course-direction-advisor

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

• Third-party content exposure detected (high risk: 0.90). The skill's B-market-scan default and required workflow (e.g., "Recommended Workflow" step 6: "scan public discussion, paid products, user complaints, and solution promises", plus Market Analysis and Evidence Indexing rules that demand collecting market_refs/market_links and concrete dates/links) explicitly require the agent to fetch and interpret public/user-generated web content, which can directly influence its topic-selection and decision outputs.