customer-call-to-product-work

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the required workflow uses $monologue-notes to search for and then fetch/read customer call transcripts (“monologue notes get NOTE_ID”), which are outsider-authored free text (customer communications) that the agent ingests into the LLM context for evidence extraction.