vLLM Authentication Bypass via ASGI Trust (0.3.0-0.22.0)
CVE-2026-48746 Published on June 22, 2026

vLLM: OpenAI auth bypass
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.

NVD

Vulnerability Analysis

CVE-2026-48746 is exploitable with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. An automatable proof of concept (POC) exploit exists. The potential impact of an exploit of this vulnerability is considered to have a high impact on confidentiality, with no impact on integrity, and a high impact on availability.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
NONE
User Interaction:
NONE
Scope:
UNCHANGED
Confidentiality Impact:
HIGH
Integrity Impact:
NONE
Availability Impact:
HIGH

Weakness Types

What is a HTTP Request Smuggling Vulnerability?

When malformed or abnormal HTTP requests are interpreted by one or more entities in the data flow between the user and the web server, such as a proxy or firewall, they can be interpreted inconsistently, allowing the attacker to "smuggle" a request to one device without the other device being aware of it.

CVE-2026-48746 has been classified to as a HTTP Request Smuggling vulnerability or weakness.

Trust Boundary Violation

The product mixes trusted and untrusted data in the same data structure or structured message. A trust boundary can be thought of as line drawn through a program. On one side of the line, data is untrusted. On the other side of the line, data is assumed to be trustworthy. The purpose of validation logic is to allow data to safely cross the trust boundary - to move from untrusted to trusted. A trust boundary violation occurs when a program blurs the line between what is trusted and what is untrusted. By combining trusted and untrusted data in the same data structure, it becomes easier for programmers to mistakenly trust unvalidated data.


Products Associated with CVE-2026-48746

Want to know whenever a new CVE is published for Red Hat products? stack.watch will email you.

Red Hat Ai Inference Server
 
Red Hat Exploit Intelligence
 
Red Hat Migration Toolkit Applications
 
Red Hat Openshift Lightspeed
 
Red Hat Ansible Automation Platform
 
Red Hat Enterprise Linux Ai
 
Red Hat Openshift Ai
 
Red Hat Hummingbird
 
Red Hat Satellite
 

Affected Versions

vllm-project vllm: Red Hat AI Inference Server 3.2: Red Hat AI Inference Server 3.2: Red Hat AI Inference Server 3.3: Red Hat AI Inference Server 3.3: Red Hat Exploit Intelligence: Red Hat Migration Toolkit for Applications 8: Red Hat OpenShift Lightspeed: Red Hat OpenShift Lightspeed: Red Hat OpenShift Lightspeed: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat AI Inference Server: Red Hat Ansible Automation Platform 2: Red Hat Ansible Automation Platform 2: Red Hat Ansible Automation Platform 2: Red Hat Ansible Automation Platform 2: Red Hat Ansible Automation Platform 2: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Enterprise Linux AI (RHEL AI) 3: Red Hat Hardened Images: Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat OpenShift AI (RHOAI): Red Hat Satellite 6: Red Hat Satellite 6: Red Hat Satellite 6: Red Hat Satellite 6: Red Hat Satellite 6: