← All CVEs

CVE-2026-48746

CRITICAL 9.1

Published 2026-06-22 · Last modified 2026-07-01

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.

ELEVATED IMPACT

Severe if exploited (CVSS 9.1), but no known exploitation and low modeled probability. Patch on a normal cadence.

Exploitation likelihood

0.9%chance of exploitation in 30 days · 54th percentile

○ In CISA KEV ○ Public exploit / PoC

Impact if exploited

9.1CVSS 3.1 · CRITICAL

  • ConfidentialityHigh
  • IntegrityNone
  • AvailabilityHigh

What an attacker needs

  • Access: Reachable over the network — no local access needed
  • Privileges: No account or privileges required
  • User interaction: No user interaction needed
  • Complexity: No special conditions — reliably repeatable

✓ lowers the bar for an attacker · ⚠ raises it

Affected

Vendors Vllm Project Red Hat

Products Vllm Red Hat Ai Inference Server 3.3 Exploit Intelligence Migration Toolkit For Applications 8 Openshift Lightspeed Red Hat Ai Inference Server Red Hat Ansible Automation Platform 2 Red Hat Enterprise Linux Ai (Rhel Ai) 3

Weakness (CWE)

  • CWE-444
  • CWE-501

CVSS vector

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

Sources: NVD · CVE.org · EPSS