We found results for “”
CVE-2026-22778
Good to know:
Date: February 2, 2026
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.
Severity Score
Related Resources (7)
Severity Score
Weakness Type (CWE)
Top Fix
Upgrade Version
Upgrade to version vllm - 0.14.1;https://github.com/vllm-project/vllm.git - v0.15.0
CVSS v3.1
| Base Score: |
|
|---|---|
| Attack Vector (AV): | NETWORK |
| Attack Complexity (AC): | LOW |
| Privileges Required (PR): | NONE |
| User Interaction (UI): | NONE |
| Scope (S): | UNCHANGED |
| Confidentiality (C): | HIGH |
| Integrity (I): | HIGH |
| Availability (A): | HIGH |
Vulnerabilities
Projects
Contact Us


