nvidia-dynamo
NVIDIA Dynamo orchestrates distributed LLM inference, optimizing multi-GPU deployments with intelligent routing and autoscaling capabilities.
Install this skill
or
97/100
Security score
The nvidia-dynamo skill was audited on Mar 2, 2026 and we found 3 security issues across 1 threat category. Review the findings below before installing.
Categories Tested
Security Issues
low line 38
External URL reference
SourceSKILL.md
| 38 | **GAIE Integration (v0.9.0+):** The router accepts [Gateway API Inference Extension (GAIE)](https://gateway-api.sigs.k8s.io/geps/gep-2987/) routing hints — K8s-native inference routing metadata (model |
low line 167
External URL reference
SourceSKILL.md
| 167 | Cloud-specific guides: [AWS EKS](https://github.com/ai-dynamo/dynamo/blob/main/examples/deployments/EKS), [Google GKE](https://github.com/ai-dynamo/dynamo/blob/main/examples/deployments/GKE), [Azure A |
low line 272
External URL reference
SourceSKILL.md
| 272 | export OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4317 |
Scanned on Mar 2, 2026
View Security DashboardInstall this skill with one command
/learn @tylertitsworth/nvidia-dynamo