---
title: "CVE-2025-54381: BentoML SSRF Vulnerability in File Upload Processing"
url: https://erroneo.us/security/cve/CVE-2025-54381/
description: "CVE-2025-54381 (bentoml (PyPI)): BentoML is a Python library for building online serving systems optimized for AI apps and model inference. In versions…"
type: vulnerability-record
section: "Security Digest"
date_published: 2025-07-29
date_modified: 2025-07-30
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2025-54381"
kev: false
cvss: 9.9
epss: 0.16152
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2025-54381: BentoML SSRF Vulnerability in File Upload Processing

**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 16.2% , percentile 97: FIRST’s model estimates a 16.2% chance of exploitation activity in the next 30 days, higher than 97% 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) >= 1.4.0, < 1.4.19, fixed in 1.4.19 . 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. In versions 1.4.0 until 1.4.19, the file upload processing system contains an SSRF vulnerability that allows unauthenticated remote attackers to force the server to make arbitrary HTTP requests. The vulnerability stems from the multipart form data and JSON request handlers, which automatically download files from user-provided URLs without validating whether those URLs point to internal network addresses, cloud metadata endpoints, or other restricted resources. The documentation explicitly promotes this URL-based file upload feature, making it an intended design that exposes all deployed services to SSRF attacks by default. Version 1.4.19 contains a patch for the issue.

## Affected packages

- PyPI `bentoml` >= 1.4.0, < 1.4.19 → fixed: 1.4.19

## Affected products (CVE record)

- bentoml BentoML: >= 1.4.0, < 1.4.19

## Severity

- GitHub_M CVSS 3.1: 9.9 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:L`
- GitHub CVSS 3.1: 9.9 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:L`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact partial .
- FIRST EPSS (model of 2026-10-21): 16.15% probability of exploitation activity in the next 30 days; percentile 97.

## Sources

- [GitHub Advisory GHSA-mrmq-3q62-6cc8](https://github.com/advisories/GHSA-mrmq-3q62-6cc8)
- [CVE.org record CVE-2025-54381](https://www.cve.org/CVERecord?id=CVE-2025-54381)
- [NVD entry CVE-2025-54381](https://nvd.nist.gov/vuln/detail/CVE-2025-54381)
- [github.com](https://github.com/bentoml/BentoML/security/advisories/GHSA-mrmq-3q62-6cc8)
- [github.com](https://github.com/bentoml/BentoML/commit/534c3584621da4ab954bdc3d814cc66b95ae5fb8)

---
Source page: https://erroneo.us/security/cve/CVE-2025-54381/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt