Critical severity · published Feb 2, 2026
CVE-2026-22778
vLLM is an inference and serving engine for large language models (LLMs)
9.8
CVSS
18.5%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)18.5% · higher than 97% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
Vllm · Vllm
0.8.3 before 0.14.1 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-22778
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-22778
Issue Tracking
https://github.com/vllm-project/vllm/pull/31987
Issue Tracking
https://github.com/vllm-project/vllm/pull/32319
Release Notes
https://github.com/vllm-project/vllm/releases/tag/v0.14.1
Vendor Advisory
https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv
access.redhat.com
https://access.redhat.com/errata/RHSA-2026:19712
access.redhat.com
https://access.redhat.com/errata/RHSA-2026:30087
More from Vllm
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22807
vLLM is an inference and serving engine for large language models (LLMs)
9.8
CVE-2025-47277
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache…
9.8
CVE-2025-32444
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs
9.8
CVE-2024-11041
vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function