Deserialization in Vllm-Project Vllm
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.
Vulnerability class: Insecure Deserialization
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Affected products
- Vllm-Project Vllm — versions < 0.32.0
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2026-115912?
- CVE-2026-115912 is a high-severity vulnerability in Vllm-Project Vllm, classified under Deserialization of Untrusted Data. CVSS score: 7.5/10. Published 2026-10-26.
- How severe is CVE-2026-115912?
- High severity. CVSS v3 base score is 7.5 out of 10.