tao-train-action-recognition

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were detected. The skill is authored by NVIDIA and correctly utilizes official TAO Toolkit command-line interfaces and Docker container images (tao_toolkit.pyt) for its intended purpose of video action classification.- [SAFE]: The skill's handling of datasets and configuration is restricted to standard deep learning workflows. It expects video data and structured YAML configuration, presenting no significant surface for indirect prompt injection or unauthorized data access.- [SAFE]: All external resource references, such as the nvidia-container-toolkit and TAO CLI commands, are consistent with the vendor's official documentation and legitimate use cases for machine learning development.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:40 PM
Security Audit — agent-trust-hub — tao-train-action-recognition