Strix
26.1K

CVE-2025-54381

CRITICALCVSS 9.9/10EPSS 11.11%

Last modified

CVE-2025-54381 is a critical-severity vulnerability rated 9.9/10 on the CVSS scale. 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. EPSS estimates a 11.11% chance of exploitation in the next 30 days.

Description

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.

Metrics

CVSS 3.1
9.9/10

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:L

EPSS Probability
11.11%

95.4th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
BentomlBentoml>= 1.4.0, < 1.4.19

References

Timeline

Published
Last Modified
Status
Analyzed

Frequently Asked Questions

What is CVE-2025-54381?
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.
How severe is CVE-2025-54381?
CVE-2025-54381 has a CVSS score of 9.9/10 (CRITICAL severity). The EPSS model estimates a 11.11% probability of exploitation in the next 30 days.
How do I fix CVE-2025-54381?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2025-54381?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST