vllm-project · vLLM · published 2026-06-22

CVE-2026-48746vLLM: OpenAI auth bypass

This month Public proof-of-concept exists (SSVC exploitation: poc).

CVE-2026-48746 has a public proof-of-concept exploit, but no confirmed exploitation in the wild. EPSS estimates a 1.2% chance of exploitation in the next 30 days, higher than 67% of all CVEs. This vLLM vulnerability: CVSS 9.1 (v3.1), attacks can be automated. Fixed upstream in vLLM 0.22.0. Patch in your normal monthly cycle.

Share this

Remediation#

Fixed upstream in vLLM 0.22.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.22.0

    Upgrade to 0.22.0

    Why: Public proof-of-concept exists (SSVC exploitation: poc).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)1.2% (68th pct)FIRST EPSS v2026.06.15
CVSS base score9.1 (v3.1)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
CNA / CISA ADP
SSVC exploitationpocCISA Vulnrichment
SSVC automatableYesCISA Vulnrichment
SSVC technical impactpartialCISA Vulnrichment

Affected versions (from the CVE record)#

Description (from the CVE record)#

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.

Quoted from the CVE Program record.

Elsewhere#

Distro status: Debian · Ubuntu · Red Hat · Alpine

Something wrong on this page?
Anonymous. Reports are checked against the primary source.

Also on today's list

See today's list → · Coming up →