retellai-webhooks-events

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

• Third-party content exposure detected (high risk: 0.90). The skill receives and processes webhook payloads (SKILL.md Step 2 and references/webhook-handlers.md) that include call transcripts and analysis coming from external users/third parties, and those transcripts/summaries are parsed and used to drive actions (e.g., llm.extract -> create tasks, alerting, CRM logging), exposing the agent to untrusted user-generated content that could contain indirect prompt injections.