Advisory record · GHSA-7v4r-c989-xh26

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 setti...

CVSS 9.8 CriticalCriticalEPSS 0.52 · 98th percentile

Critical, because:

  • CVSS score 9.8: 9.0 or more.
  • CVSS score 9.8 (7.0 or more) and EPSS 0.52 (0.1 or more): a high score and a real chance of exploitation in the next 30 days.

How we decide what’s critical

Published by the GitHub Advisory Database at 9 Apr 2025, 16:15 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
bentomlPyPI>=1.0.0, <1.4.81.4.8
Identifiers
GHSA-7v4r-c989-xh26 · CVE-2025-32375 · PYSEC-2025-32
Weakness (CWE)
CWE-502
Published
9 Apr 2025
Updated
10 Jun 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

BentoML versions 1.0.0 up to 1.4.8 are vulnerable to insecure deserialization in the runner server. An attacker who can send a crafted POST request to the server can execute arbitrary code, gaining initial access and the ability to disclose information. Upgrade bentoml to version 1.4.8 or later.

Written 10 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
9.8 Critical 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.52, the 98th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

This record came from the full history of the GitHub Advisory Database, published 9 Apr 2025. New records show when each source confirmed them.

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.