market-research-reports

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes calling research-lookup to fetch market research, government statistics, news, and other secondary sources, and those fetched pages/reports’ body text is then ingested into the agent’s LLM context for synthesis—i.e., outsider-authored public web/content sources via the research-lookup path.