ai-voice-cloning
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
beltCLI tool to execute remote applications for text-to-speech and audio synthesis, including models from Inworld and ElevenLabs. Examples include commands such asbelt app runandbelt login. - [EXTERNAL_DOWNLOADS]: The skill references the
inference-shrepository on GitHub for installation instructions and usesnpxto download thebelt-sh/clitool. These references point to the service provider's infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data via the
promptandtextparameters inSKILL.md. This data is passed to external inference models. The capability inventory includes remote application execution and local file writing. No boundary markers or specific sanitization steps are defined within the skill instructions to mitigate instructions potentially embedded in the processed text.
Audit Metadata