| Component | vLLM |
| Severity | high (CVSS 7.5) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H |
| Published (NVD) | 2026-10-26 |
| Affected versions | < 0.32.0 from the CVE Program record written by the CNA that assigned the CVE |
| Fixed in | 0.32.0 |
| Weakness | CWE-502 |
| CISA KEV | not listed |
NVD description
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.
What to do
- Upgrade vLLM to
0.32.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-115912
- https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0
- https://github.com/vllm-project/vllm/pull/59357
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w