Server-side Request Forgery (SSRF)

Overview bentoml is a BentoML: Build Production-Grade AI Applications Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the MultipartSerde. ensurefile and JSONSerde.parserequest processes. An attacker can cause the server to make arbitrary HTTP requests to...

GHSA-MRMQ-3Q62-6CC8 BentoML SSRF Vulnerability in File Upload Processing

Description There's an SSRF in the file upload processing system that allows remote attackers to make arbitrary HTTP requests from the server without authentication. The vulnerability exists in the serialization/deserialization handlers for multipart form data and JSON requests, which automatical...

BentoML 代码问题漏洞

BentoML is an open source modeling service library from BentoML Open Source. It is used to build high-performance and scalable artificial intelligence applications using Python. A code issue vulnerability exists in BentoML versions 1.4.0 through 1.4.19 that stems from the file upload processing...

PT-2025-31269

Name of the Vulnerable Software and Affected Versions BentoML versions 1.4.0 through 1.4.19 Description BentoML contains a Server-Side Request Forgery SSRF issue in the file upload processing system. This allows unauthenticated remote attackers to force the server to make arbitrary HTTP requests...

BentoML 1.x < 1.4.8 Arbitrary Code Execution

The version of the BentoML library installed on the remote host has an arbitrary code execution vulnerability. 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 serve...

BentoML's runner server RCE

There was an insecure deserialization in BentoML's runner server prior to version 1.4.8. By setting specific headers and parameters in the POST request, it is possible to execute unauthorized arbitrary code in the context of the user running the server, which will grant initial access and...

The vulnerability of the serde.py component in the BentoML library allows a hacker to execute arbitrary code on the server.

The vulnerability of the serde.py component in the BentoML library is related to deficiencies in the deserialization mechanism. Exploiting this vulnerability could allow a remote attacker to execute arbitrary code on the server...

📄 BentoML Runner Server Remote Code Execution

There was an insecure deserialization in BentoML's runner server prior to version 1.4.8. By setting specific headers and parameters in the POST request, it is possible to execute unauthorized arbitrary code in the context of the user running the server, which will grant initial access and...

Metasploit Wrap-Up 04/18/2025

Smaller Fetch Payloads This week, a significant enhancement was made to the already awesome fetch payload feature by our very own bwatters-r7. The improvement introduces a new option, PIPEFETCH, which optimizes the process by serving both the payload and the command to be executed simultaneously...

Remote Code Execution (RCE)

BentoML is vulnerable to Remote Code Execution RCE. The vulnerability is due to improper handling of specific headers and parameters in POST requests, which allows remote code execution RCE on the server...

BentoML RCE

A Remote Code Execution RCE vulnerability caused by insecure deserialization has been identified in v1.4.2 of BentoML. It allows any unauthenticated user to execute arbitrary code on the server. Module Options msf use exploit/linux/http/bentomlrcecve202527520 msf exploitbentomlrcecve202527520 sho...

📄 BentoML 1.4.2 Remote Code Execution

A remote code execution vulnerability caused by insecure deserialization has been identified in version 1.4.2 of BentoML. It allows any unauthenticated user to execute arbitrary code on the server. This module requires Metasploit: https://metasploit.com/download Current source:...

Remote Code Execution (RCE)

BentoML is vulnerable to Remote Code Execution RCE. The vulnerability is due to insecure deserialization due to an unsafe code segment in serde.py that allows arbitrary code execution by unauthenticated users...

BentoML Vulnerability Allows Remote Code Execution on AI Servers

TL;DR: A critical deserialization vulnerability CVSS 9.8 - CVE-2025-27520 in BentoML v1.3.8–1.4.2 lets attackers execute remote code without…...

CVE-2025-32375

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...

ai-dynamo (=0.1.0), bento-sgl-router (>=0.0.1 <=0.0.6) +22 more potentially affected by CVE-2025-32375 via bentoml (>=1.0.0a7 <=1.4.7)

bentoml PYPI version =1.0.0a7, =0.0.1, =0.2.3, =0.1.0, =0.0.1, =1.0.1, =0.1.0, =0.2.0, =0.3.12, =0.0.1, =1.0.3, =1.0.4 and more Source cves: CVE-2025-32375 Source advisory: OSV:PYSEC-2025-32...

CVE-2025-32375

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...

PYSEC-2025-32

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...

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

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...

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

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...