Skip to content
Fencer Vulns
high 7.5

CVE-2025-48956 json

vLLM API endpoints vulnerable to Denial of Service Attacks

published 2025-08-21 14 mo ago modified 2026-09-10 1 mo ago also EUVD-2025-25446 , GHSA-rxc4-3w6r-4v47 , PYSEC-2026-2021

cvss
7.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.6%
EPSS 0.6% chance of exploitation in 30 days, percentile 47%
public exploits
0
none known

Summary

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.

Patch / fix

  • pypi vllm 0.10.1.1
  • vllm-project vllm 0.10.1.1
  • vllm vllm 0.10.1.1

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2025-48956 updated cvss 7.5

vllm: HTTP header size limit not enforced allows Denial of Service from Unauthenticated requests

  • Red Hat AI Inference Server rhaiis/vllm-tpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaiis/vllm-spyre-rhel9, rhaiis-preview/vllm-cuda-rhel9
    affected: workaround, no fix available, no fix planned “Will not fix”
  • Red Hat Enterprise Linux AI (RHEL AI) rhelai1/ui-rhel9, rhelai1/gemma-2-9b-it, rhelai1/gemma-2-9b-it-fp8, rhelai1/granite-8b-lab-v1, rhelai1/pathservice-rhel9, rhelai1/skills-adapter-v3, +37 more
    affected: workaround, no fix available
  • Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9
    affected: workaround, no fix planned “Will not fix”
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-cuda-rhel9, rhoai/odh-vllm-rocm-rhel9
    affected: workaround, no fix available
  • Red Hat Enterprise Linux AI 1.5 rhelai1 1.5.4-1761043227, rhelai1 1.5.4-1761050413, rhelai1 1.5.4-1761060689, rhelai1 1.5.4-1761064179, rhelai1 1.5.4-1761073793, rhelai1 1.5.4-1761220254, +4 more
    fixed: vendor fix RHSA-2025:19427
  • Red Hat OpenShift AI 2.25 rhoai/odh-vllm-cpu-rhel9 1780069252
    fixed: vendor fix RHSA-2026:24977
  • Red Hat OpenShift AI 3.3 rhoai 1770754585, rhoai 1770754605, rhoai 1770754646, rhoai 1770956034, rhoai 1771809484, rhoai 1771840993
    fixed: vendor fix RHSA-2026:3713
  • Red Hat OpenShift AI 2.25 rhoai/odh-rhel9-operator 1780513840, rhoai/odh-dashboard-rhel9 1780467029, rhoai/odh-modelmesh-rhel9 1780069506, rhoai/odh-operator-bundle 1780514621, rhoai/odh-vllm-cuda-rhel9 1780069320, rhoai/odh-vllm-rocm-rhel9 1780069849, +70 more Red Hat OpenShift AI 3.3 rhoai 1769162595, rhoai 1769436305, rhoai 1769519975, rhoai 1770277795, rhoai 1770735854, rhoai 1770788873, +66 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
partial
Assessed
14 mo ago

Exploit prediction

0.56% chance of exploitation in the next 30 days, higher than 47% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
GitHub 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
OSV 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
>=0.1.0, <0.10.1.1
0.10.1.1

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-400 Uncontrolled Resource Consumption

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.