voice-ai-development
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code or hidden logic was detected. The skill provides legitimate technical templates for integrating voice AI services.
- [EXTERNAL_DOWNLOADS]: The skill references and provides integration code for well-known and trusted AI service providers including OpenAI, Deepgram, and ElevenLabs.
- [PROMPT_INJECTION]: The skill patterns present an indirect prompt injection surface. Ingestion points: Data enters via the vapi_webhook and the on_transcript event handler in SKILL.md. Boundary markers: None are defined to separate user input from system instructions. Capability inventory: The defined patterns include the execution of function calls (e.g., get_weather, check_order) based on processed user data. Sanitization: No input validation or escaping is demonstrated before processing user arguments.
Audit Metadata