VULNERABILITY INTELLIGENCE
CVE-2026-48746
CVSS score9.1 CRITICAL
EPSS probability1.15%
CISA KEVNot currently listed
Published2026-06-22
Last modified2026-10-25
CVSS vectorCVSS: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.
Weakness classification
- security-advisories@github.com: CWE-444
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c: CWE-501
Primary references
- security-advisories@github.com — Issue Tracking
- security-advisories@github.com — Third Party Advisory
- security-advisories@github.com — Third Party Advisory
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c