follow-up-after-call

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

• Third-party content exposure detected (high risk: 0.75). The required workflow ingests grounded call evidence from meeting_notes / document_store / external_messaging connectors (e.g., transcripts or message-thread text), which can include outsider-authored free text from customers/partners; that text is then placed into the agent’s LLM context to draft the follow-up.