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 Phase 2 "Source Discovery and Evaluation" explicitly requires searching and extracting content from public third‑party sources (e.g., Google Scholar, PubMed, JSTOR, arXiv, Wayback Machine and even Tier‑5 social media/forums) which the agent must read and evaluate to decide whether to proceed with outlining/drafting, so untrusted third‑party content can directly influence its actions.