SecuriTricks - CVE-2026-22778

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.

Product(s) Impacted

Vendor	Product	Versions
Llm	Vllm	0.8.3-0.14.0
Python	Pillow	*
Opencv	Opencv	*
Ffmpeg	Ffmpeg	*

Weaknesses

Common security weaknesses mapped to this vulnerability.

CWE-532

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.

*CPE(s)

Affected systems and software identified for this CVE.

Type	Vendor	Product	Version	Update	Edition	Language	Software Edition	Target Software	Target Hardware	Other Information
a	llm	vllm	0.8.3-0.14.0	/	/	/	/	/	/	/
a	python	pillow	/	/	/	/	/	/	/	*
a	opencv	opencv	/	/	/	/	/	/	/
a	ffmpeg	ffmpeg	/	/	/	/	/	/	/

References

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

CVSS Score

9.8 / 10

CVSS Data - 3.1

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

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

View Vector String

Timeline

Published: Feb. 2, 2026, 11:16 p.m.
Last Modified: Feb. 3, 2026, 4:44 p.m.

Status : Undergoing Analysis

CVE has been recently published to the CVE List and has been received by the NVD.

More info

Source

[email protected]

CVE-2026-22778