investigating-insider-threat-indicators

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow ingests outsider-authored free text via exported DLP/access log files (e.g., dlp_alerts.csv, access_logs.json) that are loaded at runtime and then embedded into the generated report/LLM context (e.g., alert_details/destinations/indicator detail strings), with no sanitization or provenance checks.