CVE-2026-115912vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
Descripción
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.
Datos: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Se publican tal como los indican las fuentes, en inglés.
Productos y versiones afectados
| Fabricante | Producto | Versiones | |
|---|---|---|---|
| vllm-project | vllm | < 0.32.0 |
Referencias y parches
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w PatchVendor Advisory
- https://github.com/vllm-project/vllm/pull/59357 Patch
- https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0 Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 Release Notes
Coincidencias CPE (NVD) (1)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*< 0.32.0