elevenlabs-voice-isolator

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as documentation and a set of templates for using the belt command-line interface. No malicious code or hidden instructions were found.
  • [EXTERNAL_DOWNLOADS]: The skill links to installation guides and supplementary skills within the inference-sh GitHub organization. These are official vendor resources and are considered safe.
  • [COMMAND_EXECUTION]: Shell commands are restricted to the belt utility for running audio processing applications. This usage is transparent and aligns with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill ingests external audio URLs for processing. While this creates a potential surface for indirect prompt injection if the audio content contains malicious instructions intended for an LLM during subsequent transcription tasks, this risk is inherent to the audio-processing functionality and is managed by the agent's runtime protections.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 10:08 AM
Security Audit — agent-trust-hub — elevenlabs-voice-isolator