tao-train-action-recognition

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows established patterns for AI model orchestration and deployment. It provides configuration schemas and templates that are used by the agent to construct valid commands for the NVIDIA TAO Toolkit.
  • [COMMAND_EXECUTION]: The skill defines commands to be executed via the action_recognition CLI. These commands are restricted to the primary purpose of the skill (training, evaluation, inference) and do not involve arbitrary command execution or shell injection patterns.
  • [DATA_EXPOSURE]: While the skill includes placeholders for encryption keys and dataset paths in its templates and schemas, no sensitive credentials or hardcoded secrets are present in the skill's own content. It correctly instructs the user/agent to provide these at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:35 PM
Security Audit — agent-trust-hub — tao-train-action-recognition