content-research-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Conduct Research" / "Research Assistance" steps explicitly instruct the agent to search for, extract, and cite information from public sources (e.g., HackerNews, arXiv, Stack Overflow surveys, Anthropic/OpenAI blogs and other web publications), so it will ingest untrusted third‑party/user‑generated content as part of its workflow.