Cyber Resilience

CVE-2025-32375

CriticalPublic PoCRCE

Published: 09 April 2025

Published
09 April 2025
Modified
22 April 2025
KEV Added
Patch
CVSS Score v3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.6524 98.5th percentile
Risk Priority 59 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-32375 is a critical-severity Deserialization of Untrusted Data (CWE-502) vulnerability in Bentoml Bentoml. Its CVSS base score is 9.8 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 1.5% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Supply Chain and Deployment risk domain.

Deeper analysis

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to version 1.4.8, the runner server component contained an insecure deserialization flaw (CWE-502) that could be triggered over the network without authentication. The issue carried a CVSS score of 9.8 and allowed remote code execution through crafted requests.

An unauthenticated attacker can exploit the vulnerability by sending a POST request containing specific headers and parameters that cause the server to deserialize attacker-controlled data. Successful exploitation grants arbitrary code execution on the runner server, resulting in initial access and potential information disclosure.

The vulnerability is fixed in BentoML 1.4.8, as stated in the GitHub Security Advisory GHSA-7v4r-c989-xh26. The current EPSS score of 0.6524 with a recorded peak of 0.6911 indicates sustained exploitation interest after disclosure.

EU & UK References

Vulnerability details

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Supply Chain and Deployment
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: ai, bentoml

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
Why these techniques?

Insecure deserialization in BentoML's runner server enables remote arbitrary code execution via crafted POST requests with specific headers and parameters, facilitating initial access through exploitation of a public-facing application.

Affected Assets

bentoml
bentoml
1.0.0 — 1.4.8

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

addresses: CWE-502

Penetration testing supplies malicious serialized objects, detecting unsafe deserialization and supporting corrective actions.

addresses: CWE-502

Evaluation of untrusted data handling (deserialization testing) reveals unsafe processing, which the required remediation process addresses.

addresses: CWE-502

Untrusted serialized data can be deserialized and observed inside the chamber, blocking gadget-chain exploitation outside the sandbox.

addresses: CWE-502

Validates or rejects untrusted serialized data before deserialization occurs.

addresses: CWE-502

Identifies and blocks malicious code introduced through deserialization of untrusted data at system boundaries.

addresses: CWE-502

Integrity verification of serialized information can detect tampering before deserialization occurs.

addresses: CWE-502

Provenance of associated data allows detection of untrusted sources before deserialization or processing occurs.

References