CVE-2026-48746
Fixed in a distro release EPSS 1%CVSS 9.1
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.
Products: vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server 3.3, Red Hat Ansible Automation Platform 2.6, Red Hat Ansible Automation Platform 2.7, Red Hat Migration Toolkit for Applications 8.2, Red Hat OpenShift AI 2.25, Red Hat Exploit Intelligence, Red Hat OpenShift Lightspeed, Red Hat AI Inference Server, Red Hat Ansible Automation Platform 2, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat Hardened Images, Red Hat OpenShift AI (RHOAI), Red Hat Satellite 6
Fixed upstream
| Ecosystem | Package | Fixed in |
|---|---|---|
| PyPI | vllm | 0.22.0 |
Distro releases
| Release | Package | Fixed in |
|---|---|---|
| Chainguard | lmcache-cuda-12.8 | no fix |
| Chainguard | nemo-rl-cuda-13.0-vllm | no fix |
| Chainguard | py3.10-vllm-cuda-12.4 | 0.18.1-r4 |
| Chainguard | py3.10-vllm-cuda-12.9 | 0.19.1-r1 |
| Chainguard | py3.10-vllm-cuda-13.0 | 0.20.2-r1 |
| Chainguard | py3.12-vllm-cuda-12.4 | 0.18.1-r4 |
| Chainguard | py3.12-vllm-cuda-12.9 | 0.19.1-r1 |
| Chainguard | py3.12-vllm-cuda-13.0 | 0.20.2-r1 |
| Chainguard | py3.13-vllm-cuda-12.9 | 0.19.1-r1 |
| Chainguard | py3.13-vllm-cuda-13.0 | 0.20.2-r1 |
| Chainguard | tritonserver-backend-vllm-cuda-12.9 | no fix |
| Chainguard | tritonserver-backend-vllm-cuda-13.0 | 25.11-r10 |
| Chainguard | vllm-openai-cuda-12.9 | 0.28.0-r0 |