Skip to content
fr Sign in
9.1 Critical

CVE-2026-48746 vLLM is an inference and serving engine for large language models (LLMs)

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.

Affected products and versions

Product Affected versions Fixed in
vllm 0.3 0.3.0 → < 0.22.0 0.22.0
Red Hat AI Inference Server 3.3 1782352847 earliest → < 1782352847 1782352847
Exploit Intelligence Versions not published
Migration Toolkit for Applications 8 Versions not published
OpenShift Lightspeed Versions not published
Red Hat AI Inference Server Versions not published
Red Hat Ansible Automation Platform 2 Versions not published
Red Hat Enterprise Linux AI (RHEL AI) 3 Versions not published
Red Hat OpenShift AI (RHOAI) Versions not published
Show the 8 other branches
Product Affected versions Fixed in
Red Hat Hardened Images Versions not published
Red Hat Satellite 6 Versions not published
Red Hat AI Inference Server 3.2 1787884873 earliest → < 1787884873 1787884873
Red Hat AI Inference Server 3.2 1782951244 earliest → < 1782951244 1782951244
Red Hat Ansible Automation Platform 2.6 1783920640 earliest → < 1783920640 1783920640
Red Hat Ansible Automation Platform 2.7 1783918403 earliest → < 1783918403 1783918403
Red Hat OpenShift AI 2.25 1783082430 earliest → < 1783082430 1783082430
Red Hat Migration Toolkit for Applications 8.2 1784109883 earliest → < 1784109883 1784109883

References

Timeline

  1. Published
  2. Last modified

Other CVEs of vllm

The 121 CVEs of vllm →
CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Low CVE-2026-115916 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 High
Track this CVE