CVE-2026-48746

Published Jun 22, 2026

Last updated 5 days ago

Overview

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.
Source
security-advisories@github.com
NVD status
Modified
Products
vllm

Risk scores

CVSS 3.1

Type
Secondary
Base score
9.1
Impact score
5.2
Exploitability score
3.9
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Severity
CRITICAL

Weaknesses

security-advisories@github.com
CWE-444
0b0ca135-0b70-47e7-9f44-1890c2a1c46c
CWE-501

Social media

Hype score
Not currently trending

Configurations