CVE-2026-48746
CVE-2026-48746
9.1
CriticalPublished:
Last updated:
Source:security-advisories@github.com
Analyzed
Weakness (CWE)
CVSS Vector
v3.1- Attack Vector
- Network
- Attack Complexity
- Low
- Privileges Required
- None
- User Interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- None
- Availability
- High
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.
References
security-advisories@github.com
https://github.com/vllm-project/vllm/pull/43426security-advisories@github.com
https://github.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6security-advisories@github.com
https://x41-dsec.de/lab/advisories/x41-2026-002-starlette134c704f-9b21-4f2e-91b3-4a467353bcc0
https://x41-dsec.de/lab/advisories/x41-2026-002-starlette