ae-handoff-brief

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

• Third-party content exposure detected (high risk: 0.78). Outsider free text is ingested via Clari call summaries (clari_get_call_summary) and competitive intel threads (search_threads), which can include verbatim/AI-generated content from prospect/other non-user participants; this text is then synthesized into the AE brief and inserted into the LLM context.