PrivacyHigh
CVE-2026-48746: vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a…
- Occurred
- Jun 22, 2026
- Published
- Jun 22, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-48746
- cvss:CRITICAL
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Authentication bypass vulnerability allows unauthorized API access, constituting a security breach and potential data exposure.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8