nemotron-transcribe
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed as a documentation and routing tool for model facts and workflow selection for the Nemotron 3.5 Transcribe model family. It does not contain any executable code or direct shell commands.
- [EXTERNAL_DOWNLOADS]: The skill references official model checkpoints on Hugging Face (huggingface.co/nvidia/) and source code assets in the NVIDIA-NeMo Speech GitHub repository. These downloads and references are from a well-known vendor (NVIDIA) and are documented for user reference in accordance with standard development practices.
- [COMMAND_EXECUTION]: No shell commands or script execution patterns were found within the provided files. The instructions focus on providing metadata and routing users to canonical external scripts.
- [CREDENTIALS_UNSAFE]: There are no hardcoded API keys, secrets, or sensitive file paths. The skill explicitly instructs against the exposure of credentials or internal paths.
Audit Metadata