vLLM: OpenAI auth bypass
28Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 9.1epss 1.2%
exploitation probability
1.2%top 36% of all CVEs
observed exploitation
nono source reports it
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:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Affected products
vllm-project · vllmReferences
https://access.redhat.com/errata/RHSA-2026:30088https://access.redhat.com/errata/RHSA-2026:30089https://access.redhat.com/errata/RHSA-2026:36005https://access.redhat.com/errata/RHSA-2026:36006https://access.redhat.com/errata/RHSA-2026:42132https://access.redhat.com/errata/RHSA-2026:42142https://access.redhat.com/errata/RHSA-2026:42644https://access.redhat.com/errata/RHSA-2026:43038https://access.redhat.com/security/cve/CVE-2026-48746https://bugzilla.redhat.com/show_bug.cgi?id=2491581https://github.com/vllm-project/vllm/pull/43426https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6