design-extractor

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow explicitly requires inspecting external references such as "R1: <path, URL, screenshot, Figma frame, CSS file, token file, or note>" (Step 1) and even lists "extract a design system from an existing app or website" (When to use), meaning the agent will fetch/read untrusted public URLs or third‑party Figma/screenshots and must interpret them to make design decisions.