speech-to-text
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official SDKs (
elevenlabsfor Python and@elevenlabs/elevenlabs-jsfor Node.js) and connects to established, well-known API endpoints (https://api.elevenlabs.io). - [SAFE]: It follows security best practices by recommending the use of environment variables for API keys and single-use tokens for client-side streaming, preventing credential exposure.
- [SAFE]: Remote data ingestion is limited to well-known audio/video streams (e.g., NPR) or user-provided files for transcription purposes, which is the primary function of the skill.
- [SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were found.
Audit Metadata