9.1
/ 10
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
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.
AI Analysis
Authentication bypass vulnerability in vLLM's OpenAI API AuthenticationMiddleware
Basic Information
ID
CVE-2026-48746
Source
GitHub_M
Published
Jun 22, 2026 at 21:57
Affected Product
Vendor
vllm-project
Product
vllm
Version
>= 0.3.0, < 0.22.0
Affected Versions
vllm-project vllm >= 0.3.0, < 0.22.0
CWE Classification
AI Assessment
AI Score
9.1 / 10
AI Severity
Critical
Vendor
vllm-project
Product
vLLM
Version
0.3.0-0.22.0