z-video-study-webpage-qwen

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the --transcript / transcript.json input (user-supplied transcript text not authored by the operating user), which is sliced by transcript_for_window() and inserted into build_segment_messages() as the 该时间段转录：{transcript_text} field for each Qwen call.