tao-validate-dataset-format

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no indicators of prompt injection, obfuscation, or unauthorized data access. Its behavior is consistent with its stated purpose of providing a wrapper for dataset validation tools.
  • [COMMAND_EXECUTION]: The skill uses bash commands (tao-daft validate, tao-daft --version, python -c) to interact with the TAO DAFT utility. These operations are restricted to validating local datasets and checking tool status, which is the primary function of the skill.
  • [EXTERNAL_DOWNLOADS]: The skill references the nvidia-tao-daft package from NVIDIA. As the author is NVIDIA Corporation, this is a legitimate vendor resource used for standard package installation via pip.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:36 PM
Security Audit — agent-trust-hub — tao-validate-dataset-format