telnyx-ai-assistants-go

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

• Third-party content exposure detected (high risk: 0.90). The skill exposes the agent to untrusted third-party content via the "Import assistants from external provider" API (POST /ai/assistants/import) which pulls external assistant configurations—including their "instructions"—from third-party providers (e.g., ElevenLabs) that can materially change assistant behavior and tool use.