Skip to main content

serving-llms-vllm

Enables high-throughput LLM serving with OpenAI API compatibility, optimizing inference latency and GPU memory usage.

Install this skill

or
91/100

Security score

The serving-llms-vllm skill was audited on May 17, 2026 and we found 5 security issues across 2 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

medium line 118

Curl to non-GitHub URL

SourceSKILL.md
118curl http://localhost:9090/metrics | grep vllm
low line 48

External URL reference

SourceSKILL.md
48client = OpenAI(base_url='http://localhost:8000/v1', api_key='EMPTY')
low line 108

External URL reference

SourceSKILL.md
108# Run: locust -f test_load.py --host http://localhost:8000
low line 118

External URL reference

SourceSKILL.md
118curl http://localhost:9090/metrics | grep vllm
low line 369

External URL reference

SourceSKILL.md
369- Community: https://discuss.vllm.ai
Scanned on May 17, 2026
View Security Dashboard
Installation guide →