speech-to-text

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides official installation instructions for the ElevenLabs CLI using standard package managers (npm, Homebrew, Scoop). While it includes a shell installer command (curl ... | sh), the URL targets the official ElevenLabs GitHub repository (github.com/elevenlabs/cli), which is an expected and safe source for this vendor's tools.
  • [COMMAND_EXECUTION]: The skill provides examples for using the elevenlabs CLI to perform transcription tasks. These are standard usage examples for the documented service.
  • [REMOTE_CODE_EXECUTION]: The skill demonstrates how to transcribe audio from a remote URL using the stream_url and source_url parameters. This is a primary feature of the speech-to-text service and involves sending the remote media to the ElevenLabs API for processing, which is standard for this type of agent skill.
  • [CREDENTIALS_UNSAFE]: The documentation correctly follows security best practices by advising users to set the ELEVENLABS_API_KEY as an environment variable rather than hardcoding it. It also explains how to generate single-use tokens for client-side implementations to avoid exposing API keys in browser environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 04:37 AM
Security Audit — agent-trust-hub — speech-to-text