telnyx-voice-gather-python

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

• Third-party content exposure detected (high risk: 0.90). The skill's documented AI gather and assistant flows (e.g., POST /calls/{call_control_id}/actions/gather_using_ai and the AI assistant start/add messages endpoints plus the CallAIGather* webhook handling shown in SKILL.md) ingest callers' untrusted, user-generated speech/message_history and use those inputs to drive assistant behavior, so third-party content can materially influence actions.