ai-voice-cloning

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions from a GitHub repository and directs the user to install a skill package from the belt-sh organization.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to run voice synthesis applications, which involves executing shell commands with user-defined parameters.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text strings to generate speech, representing an attack surface where untrusted data could contain instructions intended for the processing agent. 1. Ingestion points: The prompt and text fields in the JSON input for the belt command (SKILL.md). 2. Boundary markers: No explicit delimiters or safety instructions are used to separate user data from the processing logic. 3. Capability inventory: Shell command execution via the belt tool. 4. Sanitization: The skill does not describe any validation or filtering of the input text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — ai-voice-cloning