ai-voice-cloning
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install external dependencies such as the
beltCLI vianpx skills add belt-sh/cliand refers to an installation instruction script hosted athttps://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. - [COMMAND_EXECUTION]: The skill uses the
beltCLI tool to run various AI voice models through shell commands (e.g.,belt app run inworld/text-to-speech-2). - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate audio, which presents a surface for indirect prompt injection.
- Ingestion points: User input provided via the
promptandtextfields in JSON payloads for thebeltcommand. - Boundary markers: Commands use structured JSON to encapsulate user text, which provides basic delimitation.
- Capability inventory: The skill uses
Bash(belt *)to execute remote applications for audio synthesis and media merging. - Sanitization: No specific sanitization or filtering of the input text is mentioned in the documentation.
Audit Metadata