Back to overview

CVE-2026-48746

CRITICAL
9.1
CVSS 3.1
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.

Metadata

CVE ID
CVE-2026-48746
State
PUBLISHED
Assigner
GitHub_M
Reserved
2026-05-22 19:10 UTC
Published
2026-06-22 21:57 UTC
Last updated
2026-06-22 21:57 UTC
Primary CWE
CWE-444
CWE-444: Inconsistent Interpretation of HTTP Requests ('HTTP…
Vendor / Product
vllm-project / vllm
Sources
cve.org  ·  NVD

Severity & Metrics

9.1 CRITICAL CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Affected products (1)
VendorProductPlatformVersions
vllm-project vllm >= 0.3.0, < 0.22.0
Weakness (CWE)
CWESourceDescription
CWE-444 cna CWE-444: Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling')
CVSS scores (1)
ScoreSeverityVersionSourceVector
9.1 CRITICAL 3.1 cna CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
References (3)
Back to overview