vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.
References
Configurations
History
No history.
Information
Published : 2026-06-22 23:16
Updated : 2026-09-16 13:18
NVD link : CVE-2026-48746
Mitre link : CVE-2026-48746
CVE.ORG link : CVE-2026-48746
JSON object : View
Products Affected
vllm
- vllm
