elevenlabs-stt

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation steps from the official GitHub repository for the inference-sh platform.
  • [COMMAND_EXECUTION]: Employs the belt command-line interface to interact with transcription models. The execution scope is restricted to the specific authorized CLI tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external audio URLs and provided text strings for transcription and alignment tasks. This is an inherent part of speech-to-text functionality, and the output is treated as data for display or further processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — elevenlabs-stt