meeting-insights-analyzer

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

• Third-party content exposure detected (high risk: 0.75). The required workflow instructs the agent to scan and read user-provided transcript files from a local folder (e.g., .txt/.md/.vtt/.srt/.docx) and then quote “actual quote from transcript” into the LLM context; this is outsider-authored free text if those transcripts include contributions from people other than the operating user.