CVE-2026-22778
Last modified
CVE-2026-22778 is a critical-severity vulnerability rated 9.8/10 on the CVSS scale. 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. EPSS estimates a 3.28% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.8.3, < 0.14.1 |
References
- https://github.com/vllm-project/vllm/pull/31987Issue Tracking, Patch
- https://github.com/vllm-project/vllm/pull/32319Issue Tracking, Patch
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-22778?
How severe is CVE-2026-22778?
How do I fix CVE-2026-22778?
Are you affected by CVE-2026-22778?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST