deep-research-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill collection explicitly performs web searches, scraping, and ingestion of public web/academic sources (e.g., gpt-researcher-guide: "searches, scrapes, and filters content" and requires search providers like TAVILY/SERPER; local-deep-research-guide: "queries Google Scholar, arXiv, PubMed, Wikipedia, web" and deep-searcher-guide shows adding a WebSearchSource), so the agent will read and act on untrusted, user-generated/public third‑party content that can materially influence its iterative research actions.