design-director

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and "Read[s] ... attached images / Figma URLs" as first‑class inputs (see SKILL.md "Accepts pasted images (Claude vision), text, or Figma URLs" and Mode 6 "Design Critique" inputs), and requires the agent to read and interpret those user‑provided Figma/images to produce actionable fixes and next‑step tool suggestions, so untrusted third‑party content can materially influence decisions.