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-tools field to restrict the agent's execution environment to only the belt CLI 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
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — ai-voice-cloning