apply-interview-prep

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow for apply-interview-prep is user-input driven (the user’s interview/shortlisting context, answers, and drafts are consumed to triage assessor type and build/refine the mock interview), so outsider-authored free text can enter the monitored ingestion path directly.