---
title: "CVE-2025-27520: BentoML Allows Remote Code Execution (RCE) via Insecure Deserialization"
url: https://erroneo.us/security/cve/CVE-2025-27520/
description: "CVE-2025-27520 (bentoml (PyPI)): BentoML is a Python library for building online serving systems optimized for AI apps and model inference. A Remote Code…"
type: vulnerability-record
section: "Security Digest"
date_published: 2025-04-04
date_modified: 2025-04-04
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2025-27520"
kev: false
cvss: 9.8
epss: 0.4062
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2025-27520: BentoML Allows Remote Code Execution (RCE) via Insecure Deserialization

**Signal:** High exploit likelihood. EPSS ranks it in the top 5% of all CVEs for likely exploitation in the next 30 days. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 40.6% , percentile 99: FIRST’s model estimates a 40.6% chance of exploitation activity in the next 30 days, higher than 99% of all scored CVEs (very high). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes bentoml (PyPI) >= 1.3.4, < 1.4.3, fixed in 1.4.3 . Check your lockfile, including transitive dependencies.

## What it is

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. A Remote Code Execution (RCE) vulnerability caused by insecure deserialization has been identified in the latest version (v1.4.2) of BentoML. It allows any unauthenticated user to execute arbitrary code on the server. It exists an unsafe code segment in serde.py. This vulnerability is fixed in 1.4.3.

## Affected packages

- PyPI `bentoml` >= 1.3.4, < 1.4.3 → fixed: 1.4.3

## Affected products (CVE record)

- bentoml BentoML: >= 1.3.4, < 1.4.3

## Severity

- GitHub_M CVSS 3.1: 9.8 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`
- GitHub CVSS 3.1: 9.8 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 40.62% probability of exploitation activity in the next 30 days; percentile 99.

## Sources

- [GitHub Advisory GHSA-33xw-247w-6hmc](https://github.com/advisories/GHSA-33xw-247w-6hmc)
- [CVE.org record CVE-2025-27520](https://www.cve.org/CVERecord?id=CVE-2025-27520)
- [NVD entry CVE-2025-27520](https://nvd.nist.gov/vuln/detail/CVE-2025-27520)
- [github.com](https://github.com/bentoml/BentoML/security/advisories/GHSA-33xw-247w-6hmc)
- [github.com](https://github.com/bentoml/BentoML/commit/b35f4f4fcc53a8c3fe8ed9c18a013fe0a728e194)

---
Source page: https://erroneo.us/security/cve/CVE-2025-27520/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt