market-research-reports

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly calls the research-lookup integration (e.g., python skills/research-lookup/scripts/research_lookup.py) to ingest market data and citations from public third-party sources—market reports, government statistics, company filings, news/trade publications—which the agent is expected to read and use in its analysis, so it clearly consumes untrusted external web content that could carry indirect prompt injection.