elevenlabs-dialogue
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include installing the
beltCLI from npm and additional skill definitions from theinference-shGitHub repository. These are official sources for the platform's functionality. - [COMMAND_EXECUTION]: The skill utilizes the
beltCLI for audio generation, application management, and authentication. Command access is restricted in the YAML frontmatter to thebelttool only, limiting the potential for arbitrary command execution. - [SAFE]: No malicious patterns such as hardcoded credentials, data exfiltration, or obfuscation were detected. All operations are consistent with the skill's stated purpose of providing an interface for ElevenLabs and inference.sh audio services.
Audit Metadata