SecBoard
Zurück zur CVE-Übersicht

CVE-2026-48746

CRITICAL(9.1)

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

Risk Signal Score23/100 — NIEDRIG
  • CVSS 9.1 — Kritisch

EPSS-Score

1%

Exploit-Wahrscheinlichkeit (30 Tage)

CVSS Score

9.1

Technische Schwere

Beschreibung

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.

GitHub Advisories

GHSA-94f4-hr76-p5j6CRITICAL

vLLM: OpenAI auth bypass

pip/vllm→ 0.22.0
GitHub Advisory

Referenzen