CVE-2026-48746 PUBLISHED

vLLM: OpenAI auth bypass

Assigner: GitHub_M
Reserved: 22.05.2026 Published: 22.06.2026 Updated: 23.06.2026

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.

Metrics

CVSS 3.1

CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
CVSS Score: 9.1

Attack Vector	Network	Scope	Unchanged
Attack Complexity	Low	Confidentiality Impact	High
Privileges Required	None	Integrity Impact	None
User Interaction	None	Availability Impact	High

CVSS 3.1

Product Status

Vendor	vllm-project
Product	vllm
Versions	Version >= 0.3.0, < 0.22.0 is affected

References

https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6
https://github.com/vllm-project/vllm/pull/43426
https://x41-dsec.de/lab/advisories/x41-2026-002-starlette

Problem Types

CWE-444: Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling') CWE