CVE-2026-48746
EUVD-2026-3840122.06.2026, 23:16
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 (NVD)
| Vendor | Product | Version |
|---|---|---|
| vllm | vllm | 0.3.0 ≤ 𝑥 < 0.22.0 |
𝑥
= Vulnerable software versions
Early Detection
Affected products identified ahead of NVD analysis through intelligence sources.
| Vendor | Product | Version | Source |
|---|---|---|---|
| Red Hat | Red Hat AI Inference Server 3.2 | 1782951012 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat AI Inference Server 3.2 | 1782951244 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat AI Inference Server 3.3 | 1782353093 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat AI Inference Server 3.3 | 1782352847 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat Ansible Automation Platform 2.6 | 1783920640 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat Ansible Automation Platform 2.7 | 1783918403 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat Migration Toolkit for Applications 8.2 | 1784109883 ≤ 𝑥 < * | ADP |
| Red Hat | Red Hat OpenShift AI 2.25 | 1783082430 ≤ 𝑥 < * | ADP |
Common Weakness Enumeration
- CWE-444 - Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling')The product acts as an intermediary HTTP agent (such as a proxy or firewall) in the data flow between two entities such as a client and server, but it does not interpret malformed HTTP requests or responses in ways that are consistent with how the messages will be processed by those entities that are at the ultimate destination.
- CWE-501 - Trust Boundary ViolationThe product mixes trusted and untrusted data in the same data structure or structured message.
References