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 clearly ingests untrusted user-generated content — e.g., caller speech and message history provided to the AI assistant via the "Start AI Assistant"/"Add messages to AI Assistant" endpoints and delivered in webhooks like CallAIGatherEnded / CallAIGatherMessageHistoryUpdated (data.payload.message_history), and it also accepts arbitrary audio URLs in gather_using_audio — which the agent is expected to read/interpret and that can influence subsequent actions.