tao-validate-dataset-format

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill's operations are confined to dataset validation using vendor-provided tools.
  • [COMMAND_EXECUTION]: The skill uses the tao-daft command-line utility to perform structural and schema validation on datasets. This is the primary function of the skill and utilizes an official tool from the author (NVIDIA).
  • [EXTERNAL_DOWNLOADS]: The instructions describe installing the nvidia-tao-daft Python package from a standard registry. This package is a vendor-owned resource required for the skill's operation.
  • [DATA_EXPOSURE]: The skill processes dataset files at a user-specified path. This ingestion is necessary for the validation task and does not involve unauthorized data access or exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 05:47 PM
Security Audit — agent-trust-hub — tao-validate-dataset-format