skills/openlark/skills/voxcpm/Gen Agent Trust Hub

voxcpm

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical guide for the VoxCPM2 tokenizer-free TTS model developed by OpenBMB.
  • [EXTERNAL_DOWNLOADS]: Provides instructions to download software from public source code repositories (GitHub) and package registries (PyPI). Specifically, it references the OpenBMB and vLLM-project organizations, which are standard in the AI research community.
  • [COMMAND_EXECUTION]: Includes CLI examples for speech generation, voice cloning, and model fine-tuning. These commands are scoped to the model's functionality and do not exhibit malicious patterns or privilege escalation.
  • [DATA_EXFILTRATION]: No unauthorized network operations or access to sensitive local files were detected. Deployment examples use local network addresses for OpenAI-compatible API serving.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:17 AM
Security Audit — agent-trust-hub — voxcpm