Description
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.
Metrics
CVSS 3.1 9.1/10
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:HWeakness enumeration
Affected software
No affected versions have been published.
Timeline
- Published
- Jun 22, 2026
- Last modified
- Sep 16, 2026
- NVD status
- Modified