1. Home
  2. CVE Database
  3. CVE-2026-48746
CRITICAL · 9.1

CVE-2026-48746

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 authenticat...

Vulnerability 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.

CVSS Score

9.1

CRITICAL

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
NONE
Availability
HIGH

Affected Products

VendorProductVersions
VllmVllm>= 0.3.0, < 0.22.0

Related Weaknesses (CWE)

CWE-501CWE-444

References

FAQ

What is CVE-2026-48746?

CVE-2026-48746 is a vulnerability with a CVSS score of 9.1 (CRITICAL). 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 authenticat...

How severe is CVE-2026-48746?

CVE-2026-48746 has been rated CRITICAL with a CVSS base score of 9.1/10. This is considered a critical vulnerability requiring immediate attention.

Is there a patch for CVE-2026-48746?

Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.