design-system-patterns

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

• Third-party content exposure detected (high risk: 0.80). The skill's UI Audit mode explicitly accepts a "live URL" as input ("Mode 2: /ui-audit — User shares existing UI ... or live URL") which requires the agent to read and interpret arbitrary public webpages as part of its audit workflow, allowing untrusted third‑party content to materially influence decisions and tool use.