CVE-2026-22778
CRITICAL EPSS 88.3%
Published Feb 2, 20264mo ago · Modified Jun 17, 20261w ago
9.8 CVSS 3.1
Published Feb 2, 2026 4mo ago
Last Modified Jun 17, 2026 1w ago
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 Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality High
Integrity High
Availability High
Threat Intelligence
EPSS Exploit Probability
88.3% percentile
Exploit & Patch Status
No Known Exploit
Patch Available
Weaknesses 1
CWE-532
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| vllm | vllm | * | ≥0.8.3 – <0.14.1 |
References 4
- github.com https://github.com/vllm-project/vllm/pull/31987
- github.com https://github.com/vllm-project/vllm/pull/32319
- github.com https://github.com/vllm-project/vllm/releases/tag/v0.14.1
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv
Remediation
- github.com https://github.com/vllm-project/vllm/pull/31987
- github.com https://github.com/vllm-project/vllm/pull/32319