market-sizing

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow is to use “macro data sources” such as government statistics, industry association reports, analyst reports, and public company filings; these are typically fetched/ingested as external public text (outsider-authored) into the agent’s LLM context for analysis and citation.