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 installation instructions and related tools hosted on the official
inference-shGitHub repository. It also suggests installing a CLI component usingnpx. These are functional dependencies required for the skill's operation. - [COMMAND_EXECUTION]: The skill uses the
beltCLI to run voice transformation tasks. Theallowed-toolsconfiguration in the frontmatter restricts shell access exclusively to thebeltcommand, which follows the principle of least privilege. - [INDIRECT_PROMPT_INJECTION]: The skill processes external audio files via URLs, which represents a potential attack surface for indirect injection if the processing engine were vulnerable to audio-embedded instructions.
- Ingestion points: The
audioinput parameter in thebelt app runcommands (SKILL.md). - Boundary markers: None present.
- Capability inventory: Restricted shell execution via
Bash(belt *)(SKILL.md). - Sanitization: None identified; the skill relies on the remote platform (inference.sh) for audio processing and sanitization.
Audit Metadata