CVE-2026-115912 Details
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.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Oct 26, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-502 | Deserialization of Untrusted Data | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| vllm vllm | < 0.32.0 |
CPE
Remediation
| |
Change History
3 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Oct 28, 2026 | Initial Analysis | [email protected] |
| Oct 26, 2026 | CVE Modified | CISA-ADP |
| Oct 26, 2026 | New CVE Received | [email protected] |