hebrew-voice-bot-builder
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected during the analysis of the skill instructions and bundled scripts.
- [EXTERNAL_DOWNLOADS]: The skill integrates with well-known and trusted service providers (OpenAI, Google Cloud, Azure, Twilio, ElevenLabs) for speech-to-text, text-to-speech, and telephony. These are standard dependencies for the skill's primary purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an architecture for processing untrusted user audio/speech. While this creates a surface for indirect prompt injection (e.g., a caller attempting to influence the bot's behavior via spoken instructions), the skill follows industry-standard patterns for voice bot implementation.
Audit Metadata