design-method

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

• Third-party content exposure detected (medium risk: 0.30). In references/moves/generate.md, the required runtime workflow reads outsider-authored content by browsing client-provided “sector sites” via browser_serp_batch and then includes the extracted page content in the design pipeline (Step 2’s browsing and screenshot-taking), which can accept poison text.