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.
References
Configurations
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 - Patch | |
| References | () https://github.com/vllm-project/vllm/pull/59357 - Patch | |
| References | () 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 - 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
