CVE-2026-22778
9.8
CRITICAL · CVSS 3.1 · EPSS 11.2% (pctl 96)
Patch early
EPSS 11.2% — above the 10% action threshold.
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.
Scoring
| CVSS | 9.8 (CRITICAL, v3.1) |
|---|---|
| Vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| EPSS | 11.16% — more likely to be exploited than 96% of all CVEs |
| Weakness | CWE-532 |
| On CISA KEV | no |
| Public exploit | none known |
| Published | 2026-02-02 |
| Last modified | 2026-07-15 |
Affected (1)
| Vendor | Product |
|---|---|
| vllm | vllm |
References
- 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
- https://access.redhat.com/errata/RHSA-2026:19712
- https://access.redhat.com/errata/RHSA-2026:30087
- https://access.redhat.com/errata/RHSA-2026:30088
- https://access.redhat.com/errata/RHSA-2026:30089
- https://access.redhat.com/errata/RHSA-2026:3461
- https://access.redhat.com/errata/RHSA-2026:3462
- https://access.redhat.com/errata/RHSA-2026:3713
- https://access.redhat.com/errata/RHSA-2026:3782
- https://access.redhat.com/security/cve/CVE-2026-22778
- https://bugzilla.redhat.com/show_bug.cgi?id=2436113
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-22778.json
→ the Explorer · watch your stack · NVD