tao-train-fast-foundation-stereo
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches official Docker images from the NVIDIA Container Registry (
nvcr.io). These are trusted, well-known sources for NVIDIA's AI software stack. This behavior is documented neutrally as it aligns with the skill's primary intended purpose.\n- [COMMAND_EXECUTION]: The skill provides templates for executing standard TAO Toolkit actions (train,evaluate,inference,export) viadocker run. These commands are standard for the ecosystem and are executed within isolated containers, minimizing risk to the host environment.\n- [SAFE]: A thorough analysis across all 11 threat categories confirms that the skill contains no malicious instructions. There are no signs of prompt injection, obfuscation, or credential theft. Data ingestion surfaces are restricted to expected machine learning datasets (images and structured text), which are processed by specialized computer vision tools.
Audit Metadata