9.8
CVE-2026-22778
- EPSS 3.28%
- Veröffentlicht 02.02.2026 23:16:06
- Zuletzt bearbeitet 23.02.2026 18:19:12
- Quelle security-advisories@github.com
- CVE-Watchlists
- Unerledigt
LoginvLLM leaks a heap address when PIL throws an error
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.
| Typ | Quelle | Score | Percentile |
|---|---|---|---|
| EPSS | FIRST.org | 3.28% | 0.868 |
| Quelle | Base Score | Exploit Score | Impact Score | Vector String |
|---|---|---|---|---|
| security-advisories@github.com | 9.8 | 3.9 | 5.9 |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
|
CWE-532 Insertion of Sensitive Information into Log File
The product writes sensitive information to a log file.
https://github.com/vllm-project/vllm/pull/31987
https://github.com/vllm-project/vllm/pull/32319
https://github.com/vllm-project/vllm/releases/tag/v0.14.1
https://github.com/vllm-project/vllm/security/advisories/GHSA-4r2x-xpjr-7cvv