CVE-2026-115912

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.
Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

28 Oct 2026, 15:38

Type Values Removed Values Added
CPE cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
First Time Vllm vllm
Vllm
References () https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0 - () https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0 - Patch
References () https://github.com/vllm-project/vllm/pull/59357 - () https://github.com/vllm-project/vllm/pull/59357 - Patch
References () https://github.com/vllm-project/vllm/releases/tag/v0.32.0 - () https://github.com/vllm-project/vllm/releases/tag/v0.32.0 - Release Notes
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w - () https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w - Patch, Vendor Advisory

26 Oct 2026, 17:17

Type Values Removed Values Added
New CVE

Information

Published : 2026-10-26 17:17

Updated : 2026-10-28 15:38


NVD link : CVE-2026-115912

Mitre link : CVE-2026-115912

CVE.ORG link : CVE-2026-115912


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-502

Deserialization of Untrusted Data