scrape-define

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context when the user provides a “detail page URL” (or when the site is explored) and the main agent consumes the subagent’s analysis output from .scrape/.work/{site_name}/analyze-page/detail-1.rendered.json, which is derived from outsider web page content.