academic-deep-research

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

• Third-party content exposure detected (high risk: 1.00). This skill's SKILL.md and example.md explicitly require using native web_search and web_fetch to retrieve and analyze open/public web content (e.g., "web_search count=20", "web_fetch on primary sources", and example "healthcare IT forum discussions"), so the agent will ingest untrusted third-party webpages and forum content that can materially influence subsequent analysis and actions.