CVE-2026-22778

Severity CVSS v4.0:

Pending analysis

Type:

CWE-532 Information Exposure Through Log Files

Publication date:

02/02/2026

Last modified:

02/02/2026

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&#39;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.

Impact

Vector 3.x

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H CVSS v3.1 Severity and Metrics:

Base Score: 9.80 CRITICAL
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack Vector (AV): Network
Attack Complexity (AC): Low
Privileges Required (PR): None
User Interaction (UI): None
Scope (S): Unchanged
Confidentiality (C): High
Integrity (I): High
Availability (A): High

Base Score 3.x

9.80

Severity 3.x

CRITICAL

CVE-2026-22778

Description

Impact

References to Advisories, Solutions, and Tools