CVE-2026-22778
CRITICAL 9.8EPSS 3.7%
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 v3.1
- 9.8 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - CVSS v3.1
- 9.8 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - CVSS v3.1
- 9.8 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - EPSS
- 3.72% chance of exploitation in the next 30 days, 89th percentile
- Nuclei
- critical · CWE-209
- Published
- 2026-02-02
- Updated
- 2026-07-15