Skip to main content
Public proof of conceptFix available

CVE-2026-48746

A public proof of concept exists; no exploitation attested.

  • Published2026-06-22
  • Fixed in0.22.0
  • WeaknessCWE-444 · CWE-501

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

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.

Timeline

dates in UTC
  1. 2026-06-2223:16CVE publishedNVD

Observed activity

isMalicious corpus · updated 2026-10-23 18:48 UTC
Indicators tagged with this CVE, per day0 indicators over 7 days
Block these indicators
  • Firewall list (EDL, text): https://api.ismalicious.com/edl/cve/CVE-2026-48746?format=txt
  • CSV export: https://api.ismalicious.com/edl/cve/CVE-2026-48746?format=csv
  • TAXII collection of exploited CVEs
  • The EDL and CSV take an API key on the Pro plan.

Versions per branch

NVD
Vllm
BranchAffectedFixed in
0.x≥ 0.3.0, < 0.22.00.22.0

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Distribution builds and vendor advisories

Packages from OSV.dev and products from the vendors' CSAF advisories.

version not verifiedVersions not verified: read as OSV.dev and the vendors publish them, not checked against each vendor's release list.

Vendor advisories

  • RHSA-2026:61629 Red Hat Product Security1 product fixed

    Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (ROCm)

  • RHSA-2026:61627 Red Hat Product Security2 products fixed

    Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (CUDA)

  • RHSA-2026:42142 Red Hat Product Security2 products fixed

    Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.7 Container Release Update

Full record on NVD

Fix

  1. Update Vllm to 0.22.0
  2. Vendor fix Red Hat Product Security RHSA-2026:61629 · 1 productFor more information visit https://access.redhat.com/errata/RHSA-2026:61629
  3. Vendor fix Red Hat Product Security RHSA-2026:61627 · 2 productsFor more information visit https://access.redhat.com/errata/RHSA-2026:61627
  4. Vendor fix Red Hat Product Security RHSA-2026:42142 · 2 productsBefore applying this update, make sure all previously released errata relevant to your system have been applied. For details on how to apply this update, refer to: https://docs.redhat.com/en/documentation/red_hat_ansible_automation_platform/2.7#Upgrade
  5. Workaround from the vendor Red Hat Product Security RHSA-2026:61629 · 1 productRestrict network access to the vLLM API endpoint to only trusted clients and internal networks. Implement firewall rules or network policies to limit inbound connections to the vLLM service, thereby reducing the attack surface. This operational control helps prevent unauthorized external access to …

Detection

Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof-of-concept repositories
none listed
PoC-in-GitHub

Sources

  • NVDCVE recordread 2026-10-23
  • CISA-ADPSSVC decisionpoc2026-06-23
  • OpenCVESSVC decisionpoc—
  • CNACVSS 3.19.1read 2026-10-23
  • CNAweakness (CWE)CWE-444, CWE-501read 2026-10-23
  • FIRST EPSSEPSS score1.2 %2026-10-22

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Published
2026-06-22
Last Modified
2026-09-16
NVD status
Modified

Frequently asked questions

What is CVE-2026-48746?

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.

Is CVE-2026-48746 actively exploited?

A proof-of-concept exploit exists for CVE-2026-48746, but active exploitation has not been confirmed at this time.

What is the CVSS score for CVE-2026-48746?

CVE-2026-48746 has a CVSS v3 base score of 9.1 (CRITICAL severity), with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H.

Running Red Hat Ansible Automation? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

Get alerts for this productCISA KEV additions, October 2026Search CVEs

No credit card required · No monthly cap on website lookups · 250 API requests/month

Go further

Related vulnerabilities

Same product first, then the same vendor advisory and the same publication week.

Back to CVE Database