ai-voice-cloning

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the official GitHub repository of the service provider for the required CLI tool.- [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge between user-supplied text and external AI voice generation models. This creates a surface where maliciously crafted input could potentially attempt to influence the behavior of the downstream TTS engine.
  • Ingestion points: User-provided text for speech generation is used in the prompt and text arguments of the belt command in SKILL.md.
  • Boundary markers: Absent. The input is passed directly within the JSON payload.
  • Capability inventory: Executes shell commands via the Bash tool to interact with the belt CLI.
  • Sanitization: Not observed; the skill passes raw strings to the external API.- [COMMAND_EXECUTION]: The skill heavily relies on executing shell commands via the Bash tool to perform operations such as authentication, running AI models, and merging media files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:22 PM
Security Audit — agent-trust-hub — ai-voice-cloning