Analysis and contextual insights are available on OpenCVE Cloud.
No solution or workaround provided in the CVE record.
Additional remediation guidance may be available on OpenCVE Cloud.
Tracking
Sign in to view the affected projects.
No advisories yet.
Mon, 26 Oct 2026 17:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled | |
| Weaknesses | CWE-502 | |
| References |
| |
| Metrics |
cvssV3_1
|
Subscriptions
No data.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-10-26T16:54:00.643Z
Reserved: 2026-10-23T20:21:45.107Z
Link: CVE-2026-115912
No data.
Status : Received
Published: 2026-10-26T17:17:18.910
Modified: 2026-10-26T17:17:18.910
Link: CVE-2026-115912
No data.
OpenCVE Enrichment
No data.
-
CWE-502
Deserialization of Untrusted Data