running-design-reviews

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly accepts external design artifacts via "Design artifact(s): link(s) or screenshots (e.g., Figma/prototype)" and the intake/templates reference "Link(s) to design artifact(s) (Figma/prototype)," so the agent is expected to ingest and interpret user-provided/public third-party content (e.g., Figma links), which could contain untrusted instructions.