telnyx-import-vapi

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls Telnyx’s import endpoint with provider="vapi" and a vapi API key reference, which causes Telnyx to fetch outsider-authored Vapi assistant configuration text (e.g., instructions/greeting/tool configs) from Vapi and ingest it into the agent/assistant context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The import call to https://api.telnyx.com/v2/ai/assistants/import is executed at runtime and pulls assistant configurations (including "Instructions" imported as-is) from the external Vapi provider using your Vapi API key, so fetched remote content directly controls the agent's prompts.