HomeVllmCVE-2026-22778

CVE-2026-22778

CRITICAL
9.8CVSS
Published: 2026-02-02
Updated: 2026-02-23
AI Analysis

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.

CVSS Metrics

Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack Vector
network
Complexity
low
Privileges
none
User Action
none
Scope
unchanged
Confidentiality
high
Integrity
high
Availability
high
Weaknesses
CWE-532

Metadata

Primary Vendor
VLLM
Published
2/2/2026
Last Modified
2/23/2026
Source
NIST NVD
Note: Verify all details with official vendor sources before applying patches.

Affected Products

vllm : vllm

AI-Powered Remediation

Generate remediation guidance or a C-suite brief for this vulnerability.

Executive Intelligence Brief

CVE-CVE-2026-22778 | CRITICAL Severity | CVEDatabase.com | CVEDatabase.com