meeting-recap

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests the user-provided meeting transcript (including any outsider-authored free text within it) via scripts/normalize_transcript.py reading a file path or stdin, then passes the extracted segments[].text into the agent’s LLM context for recap generation—this is an outsider-content injection surface because the transcript text is not authored by the operating user.