jetson-inference-mem-tune
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill logic is contained within a Python script that performs calculations on local hardware data to provide launch parameters.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions referencing official container images from
ghcr.io/nvidia-ai-iotandnvcr.io/nvidia. These are legitimate vendor resources used for deploying the recommended serving stacks. - [COMMAND_EXECUTION]: The skill contains example shell commands for running Docker containers. These are intended for the user to configure and launch their own model servers based on the generated recommendations.
- [DATA_EXFILTRATION]: No unauthorized data access or transmission detected. The included script reads a user-specified local audit file to generate tuning parameters.
Audit Metadata