점검 대응긴급KEV 미등록
CVE-2026-22778
vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat OpenShift AI 2.25 취약점
- 대응 우선순위
- 점검
- CVSS
- 9.8
- EPSS
- 3.68% 백분위 88.3% · 2026.06.27 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.02.03
CVSS 위험도가 높아 영향 여부를 우선 점검할 취약점
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.
공급사 vllm-project
제품 vllm, Red Hat AI Inference Server 3.2, Red Hat OpenShift AI 2.25
영향 버전 >= 0.8.3, < 0.14.1, >= 0.8.3 < 0.14.1
수정 버전 0.14.1
CVSS 벡터 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CWE CWE-209, CWE-532
EPSS 데이터 기준일 2026.06.27