voice-ai-development
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a technical reference for Voice AI development, covering integration with OpenAI, Deepgram, and ElevenLabs.
- [EXTERNAL_DOWNLOADS]: Uses well-known third-party services for transcription, synthesis, and real-time communication. All connections are made to official API endpoints (e.g., api.openai.com, livekit.cloud).
- [CREDENTIALS_UNSAFE]: Uses standard placeholders (e.g., 'sk-...', '...') for API keys in code examples, which does not constitute a security risk.
- [DATA_EXFILTRATION]: No unauthorized data access or transmission detected; network operations are limited to the intended functionality of streaming audio to established providers.
- [PROMPT_INJECTION]: The role-play instructions define a 'Voice AI Architect' persona which is purely instructional and aligned with the skill's purpose.
Audit Metadata