Review reviewCritical

CVE-2026-22778

vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server 3.3

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: 9.8
EPSS: 3.72%
CISA KEV: Not listed
Published: 2026.02.03

PRIORITY ASSESSMENT

Review review

The CVSS severity warrants an early asset and exposure review.

Known exploitationNot established by KEV

Exploit probability3.72%

Technical severityCVSS 9.8

Vulnerability overview

Affected product and versions

Product: vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server 3.3
Affected versions: >= >= 0.8.3, < 0.14.1, >= 0.8.3 < 0.14.1
Fixed versions: 0.14.1

Recommended response sequence

Confirm exposure before applying a vendor-supported change.

Full remediation guide

1
Identify
Confirm that vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server 3.3 and an affected version are present.
2
Prioritize
Combine exploitation signals with asset exposure and business criticality.
3
Remediate
Follow the vendor advisory or supported update path and preserve rollback options.
4
Verify
Recheck the version, service health, access paths, and relevant logs.

Technical data

CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CWE: CWE-209, CWE-532