CVE-2026-22778 | vLLM is an inference and serving engine for large language m… | CVSS 9.8 CRITICAL

Description

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.

Metadata

CVE ID: CVE-2026-22778
State: PUBLISHED
Assigner: GitHub_M
Reserved: 2026-01-09 18:27 UTC
Published: 2026-02-02 21:09 UTC
Last updated: 2026-07-15 01:19 UTC
Primary CWE: CWE-532
CWE-532: Insertion of Sensitive Information into Log File
Vendor / Product: vllm-project / vllm
Sources: cve.org · NVD

Severity & Metrics

9.8 CRITICAL CVSS 3.1

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

SSVC — CISA Coordinator

Exploitation: none
Automatable: yes
Tech. Impact: total

Affected products (1)

Vendor	Product	Platform	Versions
vllm-project	vllm	—	>= 0.8.3, < 0.14.1

Weakness (CWE)

CWE	Source	Description
CWE-532	cna	CWE-532: Insertion of Sensitive Information into Log File
CWE-209	adp	Generation of Error Message Containing Sensitive Information

CVSS scores (2)

Score	Severity	Version	Source	Vector
9.8	CRITICAL	3.1	cna	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
9.8	CRITICAL	3.1	adp	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References (4)

https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv
https://github.com/vllm-project/vllm/pull/31987 https://github.com/vllm-project/vllm/pull/31987
https://github.com/vllm-project/vllm/pull/32319 https://github.com/vllm-project/vllm/pull/32319
https://github.com/vllm-project/vllm/releases/tag/v0.14.1 https://github.com/vllm-project/vllm/releases/tag/v0.14.1