market-research-reports

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run research-lookup (e.g., "python skills/research-lookup/scripts/research_lookup.py ...") to fetch market research reports, government statistics, company reports and other public web sources as part of its required Phase 1 research workflow, meaning untrusted third‑party content will be ingested and used to drive analysis and actions—creating a clear avenue for indirect prompt injection.