ux-audit-rethink

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 processes arbitrary "screenshots_or_links" (including live URLs) and "user_feedback" (reviews, support tickets), which are untrusted, user-generated third‑party content the agent is expected to read and interpret as part of the audit, creating risk of indirect prompt injection.