interview-system-designer

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path hiring_calibrator.py ingests user-supplied JSON via the --input argument and processes it (including free-text fields if present) through _preprocess_interview_data → _validate_interview_record → _standardize_record, so outsider-authored text can be included and read/used by the workflow before any filtering.