9.8
CRITICAL CVSS 3.1
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
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.

INFO

Published Date :

Feb. 2, 2026, 11:16 p.m.

Last Modified :

Feb. 3, 2026, 4:44 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-22778 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Vllm vllm
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 CRITICAL [email protected]
Solution
Update vLLM to version 0.14.1 or later to fix the heap address leak.
  • Update vLLM to version 0.14.1 or later.
  • Apply security patches promptly.
  • Validate input for multimodal endpoints.
References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-22778.

URL Resource
https://github.com/vllm-project/vllm/pull/31987
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/security/advisories/GHSA-4r2x-xpjr-7cvv
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-22778 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-22778 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-22778 vulnerability anywhere in the article.

  • Daily CyberSecurity
Video of Death: Critical vLLM Flaw (CVSS 9.8) Grants Remote Code Execution

A new critical vulnerability has been discovered in vLLM, a widely used high-performance library for Large Language Model (LLM) inference. Tracked as CVE-2026-22778, this flaw carries a devastating CV ... Read more

Published Date: Feb 05, 2026 (1 day, 13 hours ago)
  • The Cyber Express
Foxit Releases Security Updates for PDF Editor Cloud XSS Vulnerabilities

Foxit Software has released security updates addressing multiple cross-site scripting (XSS) vulnerabilities affecting Foxit PDF Editor Cloud and Foxit eSign, closing gaps that could have allowed attac ... Read more

Published Date: Feb 04, 2026 (2 days, 7 hours ago)
  • The Cyber Express
Critical vLLM Flaw Exposes Millions of AI Servers to Remote Code Execution

A newly disclosed security flaw has placed millions of AI servers at risk after researchers identified a critical vulnerability in vLLM, a widely deployed Python package for serving large language mod ... Read more

Published Date: Feb 03, 2026 (3 days, 5 hours ago)

The following table lists the changes that have been made to the CVE-2026-22778 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    Feb. 02, 2026

    Action Type Old Value New Value
    Added 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.
    Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
    Added CWE CWE-532
    Added Reference https://github.com/vllm-project/vllm/pull/31987
    Added Reference https://github.com/vllm-project/vllm/pull/32319
    Added Reference https://github.com/vllm-project/vllm/releases/tag/v0.14.1
    Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.
Vulnerability Scoring Details
Base CVSS Score: 9.8
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality Impact
Integrity Impact
Availability Impact