alterlab-market-research

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 "Conduct Deep Research" in 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 filings and other public web sources which the agent must read and use to drive analyses and recommendations, exposing it to untrusted third‑party content that could carry indirect prompt injection.