voice-agents
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a technical guide for implementing voice agent architectures, specifically Speech-to-Speech and Pipeline models.
- [SAFE]: Demonstrates secure handling of sensitive credentials by utilizing environment variables for API authentication (e.g., process.env.OPENAI_API_KEY).
- [EXTERNAL_DOWNLOADS]: References standard integrations with well-known AI services such as OpenAI, Deepgram, and ElevenLabs for speech processing and language modeling.
- [PROMPT_INJECTION]: Includes example system instructions for voice assistant personas; these are legitimate configurations for the application's behavior and do not attempt to bypass security controls.
Audit Metadata