ai-voice-cloning
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes a link to a remote installation script hosted on the inference-sh GitHub repository (cli-install.md). This is a standard reference for setting up the required CLI environment for the skill's functionality.
- [COMMAND_EXECUTION]: The skill utilizes the 'belt' CLI tool via Bash. Execution is restricted in the YAML frontmatter to only allow the 'belt' command, which adheres to the principle of least privilege and prevents arbitrary command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided text strings which are then passed to the voice synthesis engine. This is the intended primary purpose of the skill.
- Ingestion points: User-supplied 'prompt' and 'text' fields in the 'belt app run' commands (SKILL.md).
- Boundary markers: None present for the text inputs.
- Capability inventory: Limited to the 'belt' CLI tool (SKILL.md).
- Sanitization: The skill relies on the underlying inference.sh platform to handle the provided text data.
Audit Metadata