ai-voice-cloning
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill configuration uses the
allowed-toolsfield to restrict the agent's execution environment to only thebeltCLI tool, minimizing the attack surface. - [EXTERNAL_DOWNLOADS]: The skill references documentation and related skills hosted on the official Inference.sh GitHub repositories (
inference-sh/skills). These are recognized as vendor-owned resources necessary for the skill's intended purpose. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text input for synthesis. While this represents a data ingestion surface, the use of structured JSON templates for the CLI arguments provides a layer of separation between instructions and data.
Audit Metadata