tao-convert-dataset-format

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is authored by NVIDIA and follows best practices for using vendor-specific CLI tools to manage DAFT datasets.
  • [SAFE]: The dependency nvidia-tao-daft is an official NVIDIA package required for the skill's primary function of dataset conversion.
  • [SAFE]: No signs of obfuscation, hidden instructions, or credential harvesting were found within the skill files or metadata.
  • [SAFE]: External references point to the official NVIDIA GitHub repository for TAO skills, which is a trusted source in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:38 PM
Security Audit — agent-trust-hub — tao-convert-dataset-format