CVE-2026-48746
Published:June 22, 2026
Updated:June 29, 2026
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 Packages
https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.3.0 <v0.22.0Fix Suggestion:
Update to version v0.22.0vllm (PYTHON):
Affected version(s) >=0.3.0 <0.22.0Fix Suggestion:
Update to version 0.22.0Related Resources (5)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.8
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
NONE
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
9.1
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
NONE
Availability
HIGH
Weakness Type (CWE)
Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling')
EPSS
Base Score:
0.74