CVE-2026-48746
CRITICAL EPSS 49.8%
Published Jun 22, 20261w ago · Modified Jun 23, 20261w ago
9.1 CVSS 3.1
Published Jun 22, 2026 1w ago
Last Modified Jun 23, 2026 1w ago
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 Details
Base Score
Exploitability
Impact
Vector string
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
Threat Intelligence
EPSS Exploit Probability
49.8% percentile
Exploit & Patch Status
No Known Exploit
No Patch Available
Weaknesses 1
CWE-444
References 3
- github.com https://github.com/vllm-project/vllm/pull/43426
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6
- x41-dsec.de https://x41-dsec.de/lab/advisories/x41-2026-002-starlette
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.