The Agent Skills Directory

[SAFE]: No malicious patterns, such as prompt injection, obfuscation, or persistence mechanisms, were detected in the skill instructions.
[SAFE]: The skill references the belt CLI and the inference.sh platform, which are the legitimate service providers for the described audio processing functionality. All external URLs and package references point to these official service domains or repositories.
[SAFE]: The skill uses the allowed-tools frontmatter to restrict the execution environment to the belt command, following the principle of least privilege.

elevenlabs-voice-isolator