review-ux-ui

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

• Third-party content exposure detected (high risk: 0.90). The skill's required input "Application to review (URL, prototype, or source code)" and procedure (e.g., run accessibility scans with axe-core/Lighthouse and evaluate live flows) require the agent to fetch and analyze arbitrary public URLs or prototypes, exposing it to untrusted third‑party content that could carry indirect prompt injections.