telnyx-voice-gather-go

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

• Third-party content exposure detected (high risk: 0.80). The skill exposes the agent to untrusted, user-generated caller content via the AI features (e.g., the "Gather using AI" endpoint and AI assistant message_history/transcription delivered in webhooks like CallAIGatherMessageHistoryUpdated), which the agent is expected to read/interpret and which can materially influence subsequent actions.