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.
References
Configurations
History
22 Jul 2026, 12:18
| Type | Values Removed | Values Added |
|---|---|---|
| References |
|
21 Jul 2026, 12:18
| Type | Values Removed | Values Added |
|---|---|---|
| References |
|
07 Jul 2026, 12:16
| Type | Values Removed | Values Added |
|---|---|---|
| References |
|
30 Jun 2026, 03:20
| Type | Values Removed | Values Added |
|---|---|---|
| CWE | CWE-501 | |
| References |
|
24 Jun 2026, 16:49
| Type | Values Removed | Values Added |
|---|---|---|
| First Time |
Vllm
Vllm vllm |
|
| CPE | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | |
| References | () https://github.com/vllm-project/vllm/pull/43426 - Issue Tracking | |
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6 - Third Party Advisory | |
| References | () https://x41-dsec.de/lab/advisories/x41-2026-002-starlette - Third Party Advisory |
23 Jun 2026, 16:17
| Type | Values Removed | Values Added |
|---|---|---|
| References |
|
|
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6 - | |
| References | () https://x41-dsec.de/lab/advisories/x41-2026-002-starlette - |
23 Jun 2026, 15:16
| Type | Values Removed | Values Added |
|---|---|---|
| References |
|
|
| References | () https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6 - |
22 Jun 2026, 23:16
| Type | Values Removed | Values Added |
|---|---|---|
| New CVE |
Information
Published : 2026-06-22 23:16
Updated : 2026-07-22 12:18
NVD link : CVE-2026-48746
Mitre link : CVE-2026-48746
CVE.ORG link : CVE-2026-48746
JSON object : View
Products Affected
vllm
- vllm
