Skip to content
fr Sign in
9.8 Critical

CVE-2026-22778 vLLM is an inference and serving engine for large language models (LLMs)

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.

Affected products and versions

Product Affected versions Fixed in
vllm 0.8 0.8.3 → < 0.14.1 0.14.1
Red Hat AI Inference Server 3.2 1772160625 earliest → < 1772160625 1772160625
Red Hat OpenShift AI 2.25 1772093237 earliest → < 1772093237 1772093237
Red Hat OpenShift AI 3.3 1770956034 earliest → < 1770956034 1770956034
Red Hat AI Inference Server Versions not published
Red Hat Enterprise Linux AI (RHEL AI) 3 Versions not published
Red Hat OpenShift AI (RHOAI) Versions not published
Red Hat AI Inference Server 3.3 1782352847 earliest → < 1782352847 1782352847

References

Timeline

  1. Published
  2. Last modified

Other CVEs of vllm

The 121 CVEs of vllm →
CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Low CVE-2026-115916 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 High
Track this CVE