capture

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow (“Drain every capture surface into one file… then run capture_triage.py/capture_audit.py on that log”) ingests user-supplied free text from the capture log’s text fields via the scripts’ --input file reads at parse_log/load_items and subsequent classification/printing.