elevenlabs-voice-isolator

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download a CLI and fetch guidelines from a GitHub repository associated with inference.sh. These references target well-known technology services and are documented for standard setup.
  • [COMMAND_EXECUTION]: The skill requires the Bash tool to execute belt commands. These commands are used to process audio files via the inference.sh platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes audio data provided via URLs.
  • Ingestion points: Input JSON within belt commands in SKILL.md.
  • Boundary markers: None explicitly defined for the JSON input.
  • Capability inventory: The skill uses Bash(belt *) to interact with an external API.
  • Sanitization: No explicit sanitization of URLs is described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:23 PM
Security Audit — agent-trust-hub — elevenlabs-voice-isolator