vLLM 0.8.3<0.14.1 Heap Leak via PIL in Multimodal Endpoint
CVE-2026-22778 Published on February 2, 2026

vLLM leaks a heap address when PIL throws an error
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.

NVD

Vulnerability Analysis

CVE-2026-22778 is exploitable with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to be critical as this vulnerability has a high impact to the confidentiality, integrity and availability of this component.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
NONE
User Interaction:
NONE
Scope:
UNCHANGED
Confidentiality Impact:
HIGH
Integrity Impact:
HIGH
Availability Impact:
HIGH

Weakness Types

Insertion of Sensitive Information into Log File

Information written to log files can be of a sensitive nature and give valuable guidance to an attacker or expose sensitive user information.

Generation of Error Message Containing Sensitive Information

The software generates an error message that includes sensitive information about its environment, users, or associated data.


Products Associated with CVE-2026-22778

You can be notified by email with stack.watch whenever vulnerabilities like CVE-2026-22778 are published in these products:

Vllm
 
Red Hat Ai Inference Server
 
Red Hat Openshift Ai
 
Red Hat Enterprise Linux Ai
 

Affected Versions

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

Exploit Probability

EPSS
1.08%
Percentile
60.87%

EPSS (Exploit Prediction Scoring System) scores estimate the probability that a vulnerability will be exploited in the wild within the next 30 days. The percentile shows you how this score compares to all other vulnerabilities.