find-customer-quotes

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

• Third-party content exposure detected (high risk: 0.85). The required workflow centers on “Meeting Transcripts” evidence: it fetches and then parses transcript-like text (including speaker labels and surrounding context) into the agent’s LLM context for quote extraction/verification, which is outsider-authored free text when the transcripts are authored by external customers/prospects.