call-recording-analyzer

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when the skill calls clari_get_call / clari_get_call_summary to read the prospect’s call transcript and AI summary (public/third-party call participants’ spoken/written content not authored by the operating user), which is then placed into the agent’s LLM context for MEDDIC scoring and coaching.