CVE-2025-32375: Insecure Deserialization leads to RCE in BentoML's runner server

Severity: critical (CVSS 9.8 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 52.4% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2025-04-09 · updated 2026-06-17
Weakness: CWE-502

Description

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.8, there was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.

Affected products

BentoML: from 1.0.0 before 1.4.8 — fixed in 1.4.8

How to fix

Upgrade to a fixed version: BentoML 1.4.8. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2025-32375 or the next vulnerability affects your stack