elevenlabs-voice-isolator
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guidelines hosted on the inference-sh GitHub repository, which is an expected source for this service.- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool to perform audio processing. Access is limited to thebeltcommand space as defined in the skill configuration.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external audio URLs in thebelt app runcommands (SKILL.md). These inputs are delimited by a JSON structure, and the skill possesses the capability to execute shell commands via thebelttool. No explicit sanitization or filtering of these external URLs is detailed in the provided instructions.
Audit Metadata