skills/nvidia/skills/tao-run-platform/Gen Agent Trust Hub

tao-run-platform

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the nvidia-tao-sdk package. This is the official Python SDK provided by the vendor (NVIDIA) for managing training workloads.
  • [COMMAND_EXECUTION]: Local helper scripts included with the skill bank (list_tao_platforms.py, resolve_tao_image.py, list_tao_models.py) are used to discover platform capabilities, resolve container images, and fetch model metadata.
  • [SAFE]: Platform credentials (e.g., LEPTON_AUTH_TOKEN, BREV_API_TOKEN, S3_SECRET_KEY) are managed via environment variables. The skill contains specific instructions for the agent to verify the existence of these variables without reading their values, which adheres to secure secret management practices.
  • [SAFE]: Installation of the required SDK is not automated; the skill explicitly instructs the agent to prompt the user for authorization before performing any pip install operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:04 PM
Security Audit — agent-trust-hub — tao-run-platform