Skip to content
Fencer Vulns
critical 9.8

CVE-2026-22778 in the critical feed json

vLLM leaks a heap address when PIL throws an error

published 2026-02-02 9 mo ago modified 2026-09-10 1 mo ago also EUVD-2026-5277 , GHSA-4r2x-xpjr-7cvv , PYSEC-2026-565

cvss
9.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
18.3%
EPSS 18.3% chance of exploitation in 30 days, percentile 97%
public exploits
1
Metasploit, plus a Nuclei check

Summary

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

Patch / fix

  • pypi vllm 0.14.1
  • Red Hat Red Hat AI Inference Server 3.2 1772160593, 1772160625
  • Red Hat Red Hat AI Inference Server 3.3 1782352847, 1782352919, 1782353093
  • Red Hat Red Hat OpenShift AI 2.25 1772093237, 1772093276, 1772093278, 1772093436
  • Red Hat Red Hat OpenShift AI 3.3 1770956034, 1778264363

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-2026-22778 updated cvss 9.8

vLLM: vLLM: Remote code execution via invalid image processing in the multimodal endpoint.

  • 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 “Out of support scope”
  • Red Hat AI Inference Server 3.2 rhaiis 1772160593, rhaiis 1772160625
    fixed: vendor fix RHSA-2026:3461
  • Red Hat AI Inference Server 3.3 rhaiis/vllm-cuda-rhel9 1782352847, rhaiis/vllm-rocm-rhel9 1782353093, rhaiis/vllm-spyre-rhel9 1782352919
    fixed: vendor fix RHSA-2026:30089
  • Red Hat OpenShift AI 2.25 rhoai 1772093237, rhoai 1772093276, rhoai 1772093278, rhoai 1772093436
    fixed: vendor fix RHSA-2026:3782
  • Red Hat OpenShift AI 3.3 rhoai 1770956034, rhoai 1778264363
    fixed: vendor fix RHSA-2026:19712
  • Red Hat AI Inference Server rhaiis/vllm-tpu-rhel9
    not affected: vulnerable code not present
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9
    not affected: vulnerable code not in execute path
  • Red Hat OpenShift AI 2.25 rhoai 1772093250, rhoai 1772093252, rhoai 1772093260, rhoai 1772093266, rhoai 1772093272, rhoai 1772093273, +60 more Red Hat OpenShift AI 3.3 rhoai 1769162595, rhoai 1769436305, rhoai 1769519975, rhoai 1770277795, rhoai 1770735854, rhoai 1770754585, +152 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

Timeline

  1. First public exploit (Metasploit auxiliary/scanner/http/vllm_multimodal_info_leak)
  2. Published

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
total
Assessed
9 mo ago

Exploit prediction

18.29% chance of exploitation in the next 30 days, higher than 97% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

CVSS scores

assigned by version score vector
CNA 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CISA ADP 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
OSV 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
>=0.8.3, <0.14.1
0.14.1

Affected products

  • vllm-project vllm
  • Red Hat Red Hat AI Inference Server 3.2
  • Red Hat Red Hat AI Inference Server 3.3
  • Red Hat Red Hat OpenShift AI 2.25
  • Red Hat Red Hat OpenShift AI 3.3
  • Red Hat Red Hat AI Inference Server
  • Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3
  • Red Hat Red Hat OpenShift AI (RHOAI)

Classification

Weakness
  • CWE-532 Insertion of Sensitive Information into Log File
  • CWE-209 Generation of Error Message Containing Sensitive Information
  • CWE-122 Heap-based Buffer Overflow

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.