content-research-writer

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Conduct Research" and examples explicitly direct the agent to "search for relevant information," "find credible sources," and add citations from public sources (e.g., McKinsey, Stack Overflow) — indicating it will fetch and ingest untrusted, user/public third‑party content as part of its workflow.