elevenlabs-voice-changer

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 external installation documentation and configuration files hosted on the official GitHub repository for the service at raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
  • [COMMAND_EXECUTION]: The skill utilizes the belt command-line utility through the Bash tool to perform voice transformation, authentication, and audio processing tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data in the form of audio URLs and processing parameters provided via JSON strings.
  • Ingestion points: Parameters passed to the --input flag in the belt command within SKILL.md.
  • Boundary markers: JSON structure and single quotes are used to delimit input data.
  • Capability inventory: The skill is restricted to executing the belt CLI tool.
  • Sanitization: Input is treated as structured JSON data for processing by the underlying application.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:23 PM
Security Audit — agent-trust-hub — elevenlabs-voice-changer