telnyx-voice-gather-curl

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests untrusted, user-generated caller content via Telnyx webhooks (e.g., data.payload.message_history, CallAIGatherPartialResults / CallAIGatherEnded) and starts an AI assistant on calls (ai_assistant_start / gather_using_ai) that reads and acts on that content as part of its workflow, so third-party input could influence agent actions.