tao-validate-dataset-format

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructs the user to install and use nvidia-tao-daft, which is a legitimate package provided by the vendor (NVIDIA) for dataset validation.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. The instructions are focused on local file validation using a specific tool.
  • [SAFE]: The metadata and benchmark files describe the skill's performance and structural quality without containing malicious instructions or deceptive content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:09 PM
Security Audit — agent-trust-hub — tao-validate-dataset-format