website-to-design-md

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly loads and inspects arbitrary live websites (user-provided URLs) using agent-browser (see SKILL.md "Always use agent-browser" and scripts/extract-browser-evidence.mjs which runs agent-browser open/eval to extract DOM, text, styles, and interaction states), so untrusted third‑party page content is ingested and used to drive synthesis and next actions.