CVE-2026-22778: 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 multimo...

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.

Metrics

CVSS 3.1

9.8/10

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

EPSS Probability

3.82%

88.8th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

Vendor	Product	Versions
Vllm	Vllm	>= 0.8.3, < 0.14.1

References

Timeline

Published: Feb 2, 2026
Last Modified: Jul 15, 2026
Status: Modified

Frequently Asked Questions

What is CVE-2026-22778?

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.

How severe is CVE-2026-22778?

CVE-2026-22778 has a CVSS score of 9.8/10 (CRITICAL severity). The EPSS model estimates a 3.82% probability of exploitation in the next 30 days.

How do I fix CVE-2026-22778?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

View all 2026CVEs →