by Kastro CVE-2026-22778
vllm-project vllm — vLLM leaks a heap address when PIL throws an error
Description · from the CVE record
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
ProductAffectedFixed inSource
vllm>= 0.8.3, < 0.14.1–CNA
Red Hat AI Inference Server 3.2see advisory1772160593redhat-SADP
Red Hat AI Inference Server 3.2see advisory1772160625redhat-SADP
Red Hat AI Inference Server 3.3see advisory1782352919redhat-SADP
Red Hat AI Inference Server 3.3see advisory1782353093redhat-SADP
Red Hat AI Inference Server 3.3see advisory1782352847redhat-SADP
Red Hat OpenShift AI 2.25see advisory1772093436redhat-SADP
Red Hat OpenShift AI 2.25see advisory1772093276redhat-SADP
Red Hat OpenShift AI 2.25see advisory1772093278redhat-SADP
Red Hat OpenShift AI 2.25see advisory1772093237redhat-SADP
Red Hat OpenShift AI 3.3see advisory1778264363redhat-SADP
Red Hat OpenShift AI 3.3see advisory1770956034redhat-SADP
Scores by source
GitHub_M (CNA)9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
redhat-SADP (CNA)9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CISA ADPSSVCExploitation: none · Automatable: yes · Technical impact: total