vLLM: OpenAI auth bypass (vllm-project vllm)
At a glance
- Source
- NVD
- EPSS
- EPSS 1.15 % · percentile 67 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Modified
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.
Weaknesses (CWE)
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
- https://access.redhat.com/security/cve/CVE-2026-48746
- https://bugzilla.redhat.com/show_bug.cgi?id=2491581
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-48746.json
- https://access.redhat.com/errata/RHSA-2026:61627
- https://access.redhat.com/errata/RHSA-2026:36005
- https://access.redhat.com/errata/RHSA-2026:61629
- https://access.redhat.com/errata/RHSA-2026:36006
- https://access.redhat.com/errata/RHSA-2026:30089
- https://access.redhat.com/errata/RHSA-2026:30088
- https://access.redhat.com/errata/RHSA-2026:42132
- https://access.redhat.com/errata/RHSA-2026:42142
- https://access.redhat.com/errata/RHSA-2026:43038
- https://access.redhat.com/errata/RHSA-2026:42644
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 3.1 | CRITICAL 9.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H | GitHub_M |
| CVSS 3.1 | CRITICAL 9.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H | redhat-SADP |
| CVSS 3.1 | CRITICAL 9.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H | NVD · security-advisories@github.com (Secondary) |
| CVSS 3.1 | CRITICAL 9.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H | NVD · 0b0ca135-0b70-47e7-9f44-1890c2a1c46c (Secondary) |
Advisories
- GHSA-94f4-hr76-p5j6 — vLLM: OpenAI auth bypass
- PYSEC-2026-226 — 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
European references
- ENISA EUVD · EUVD-2026-38401
- GCVE · GCVE-0-2026-48746
Affected configurations (NVD CPE)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*≥ 0.3.0 < 0.22.0
Affected products
| Product | Versions |
|---|---|
| vllm-project · vllm | affected >= 0.3.0, < 0.22.0 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |