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 arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.

CVSS v3 9.8 CRITICAL

9.8^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 3.9 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26	Exploit Vendor Advisory
https://github.com/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26	Exploit Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:bentoml:bentoml:*:*:*:*:*:*:*:*

History

22 Apr 2025, 16:52

Type	Values Removed	Values Added
References	~~() https://github.com/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26 -~~	() https://github.com/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26 - Exploit, Vendor Advisory
CPE		cpe:2.3:a:bentoml:bentoml::::::::
Summary		(es) BentoML es una librería de Python para crear sistemas de servicios en línea optimizados para aplicaciones de IA e inferencia de modelos. Antes de la versión 1.4.8, existía una deserialización insegura en el servidor de ejecución de BentoML. Al configurar encabezados y parámetros específicos en la solicitud POST, es posible ejecutar cualquier código arbitrario no autorizado en el servidor, lo que permite a los atacantes tener acceso inicial y divulgación de información en el servidor. Esta vulnerabilidad se corrigió en la versión 1.4.8.
First Time		Bentoml Bentoml bentoml

09 Apr 2025, 16:15

Type	Values Removed	Values Added
New CVE

Information

Published : 2025-04-09 16:15

Updated : 2025-04-22 16:52

NVD link : CVE-2025-32375

Mitre link : CVE-2025-32375

CVE.ORG link : CVE-2025-32375

JSON object : View

Products Affected

bentoml

bentoml

CWE

CWE-502

Deserialization of Untrusted Data

{"id": "CVE-2025-32375", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}]}, "published": "2025-04-09T16:15:25.580", "references": [{"url": "https://github.com/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26", "tags": ["Exploit", "Vendor Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26", "tags": ["Exploit", "Vendor Advisory"], "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Primary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-502"}]}], "descriptions": [{"lang": "en", "value": "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 arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8."}, {"lang": "es", "value": "BentoML es una librer\u00eda de Python para crear sistemas de servicios en l\u00ednea optimizados para aplicaciones de IA e inferencia de modelos. Antes de la versi\u00f3n 1.4.8, exist\u00eda una deserializaci\u00f3n insegura en el servidor de ejecuci\u00f3n de BentoML. Al configurar encabezados y par\u00e1metros espec\u00edficos en la solicitud POST, es posible ejecutar cualquier c\u00f3digo arbitrario no autorizado en el servidor, lo que permite a los atacantes tener acceso inicial y divulgaci\u00f3n de informaci\u00f3n en el servidor. Esta vulnerabilidad se corrigi\u00f3 en la versi\u00f3n 1.4.8."}], "lastModified": "2025-04-22T16:52:36.937", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:bentoml:bentoml:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "FA900784-6BEB-4584-A356-13411ECDDF9B", "versionEndExcluding": "1.4.8", "versionStartIncluding": "1.0.0"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}