ai-voice-cloning

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides a link to installation instructions hosted on GitHub (raw.githubusercontent.com/inference-sh/skills). This is a standard practice for documenting setup procedures and targets the vendor's official repository.
  • [COMMAND_EXECUTION]: The skill utilizes a specific CLI tool (belt) to interact with voice generation models. The execution environment is restricted via the allowed-tools frontmatter to this specific tool (Bash(belt *)), adhering to the principle of least privilege.
  • [PROMPT_INJECTION]: The skill accepts text input for voice synthesis. While this represents a surface for indirect prompt injection, the risk is inherent to the text-to-speech functionality and is mitigated by the use of structured JSON payloads for the underlying CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — ai-voice-cloning