summarize

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text can be ingested when the runtime path “summarize this URL/article” fetches and extracts readable page content (public web content) and/or when “summarize this YouTube/video” extracts a transcript from an external video source, which is then placed into the agent’s LLM context.