tao-run-platform

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the NVIDIA TAO SDK package.
  • Evidence: SKILL.md contains logic to check for the presence of the tao_sdk module and execute pip install "nvidia-tao-sdk[all]" if it is missing.
  • Context: This is a vendor-owned resource required for the skill's primary functionality and originates from a trusted source.
  • [COMMAND_EXECUTION]: Use of helper scripts for environment and model discovery.
  • Evidence: The skill executes local Python scripts, including list_tao_platforms.py, resolve_tao_image.py, and list_tao_models.py, to resolve runtime configurations.
  • [COMMAND_EXECUTION]: Platform-specific job submission and monitoring.
  • Evidence: The agent is instructed to use the SDK API to create, poll, and manage jobs on remote platforms, which involves executing commands for container orchestration and job scheduling.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 05:48 PM
Security Audit — agent-trust-hub — tao-run-platform