ux-review

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads user/outsider-authored UX spec files (and related referenced GDD/header content) from the tenant via a user-supplied file path argument or “all” glob, so an outsider who can submit those documents can inject free text that the LLM will ingest during validation.