tao-train-centerpose
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified during the analysis of the skill's instructions, schemas, or reference materials.
- [COMMAND_EXECUTION]: The skill documents the use of standard TAO Toolkit commands (e.g.,
centerpose train,centerpose inference) intended to be run within a Docker container. These commands are legitimate for the skill's stated purpose of model development. - [EXTERNAL_DOWNLOADS]: The skill references Docker images hosted on
nvcr.io(NVIDIA Container Registry). This is a well-known and trusted service for hosting official NVIDIA software, and the references are used for standard deployment workflows.
Audit Metadata