telnyx-import-elevenlabs

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

• Third-party content exposure detected (high risk: 0.90). The import workflow explicitly pulls agent configurations from ElevenLabs via the import endpoint (see "Interaction model" and Step 2) and "Instructions" are imported "as‑is" (see "What Gets Imported"), meaning untrusted/user-generated ElevenLabs content can be ingested and influence assistant behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes a runtime call to the Telnyx import endpoint (https://api.telnyx.com/v2/ai/assistants/import), which pulls ElevenLabs agent configurations (including instructions/greetings) into Telnyx and therefore injects external content that directly controls assistant prompts.