CVE-2025-54381
published 2025-07-29CVE-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…
PriorityP276critical9.9CVSS 3.1
AVNACLPRNUINSCCHILAL
EPSS
11.88%
95.6th percentile
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
3 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| bentoml | bentoml | — | — |
| bentoml | bentoml | >= 1.4.0 < 1.4.19 | 1.4.19 |
| bentoml | bentoml | >= 1.4.0 < 1.4.19 | 1.4.19 |
Detection & IOCsextracted from sources · hover to see the quote
- →The SSRF vulnerability is triggered via multipart form data and JSON request handlers that automatically download files from user-provided URLs — monitor for outbound HTTP requests originating from the BentoML server process to internal network addresses or cloud metadata endpoints (e.g., 169.254.169.254) following inbound multipart/JSON file upload requests. ↗
- →The SSRF is exploitable by unauthenticated remote attackers — no authentication bypass is required; any inbound request to BentoML file upload endpoints from untrusted sources should be treated as potentially malicious. ↗
- →The initial patch in version 1.4.19 was insufficient and a bypass was possible — environments running BentoML 1.4.0 through 1.4.21 remain vulnerable; detection should cover all versions prior to 1.4.22. ↗
- →The URL-based file upload feature is an explicitly documented, default-enabled design — all BentoML deployments in versions 1.4.0–1.4.18 are exposed to SSRF by default without any special configuration required by the attacker. ↗
- ·The vulnerability affects BentoML versions 1.4.0 through 1.4.18 per the NVD entry, but Tenable Research confirmed the patch in 1.4.19 was bypassable — the true fixed version is 1.4.22 or later. ↗
- ·Upgrade to BentoML 1.4.22 or later is required for a complete fix; versions 1.4.19 through 1.4.21 contain an incomplete patch with a known bypass. ↗
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
OSV
BentoML SSRF Vulnerability in File Upload Processing
osv·2025-07-29
CVE-2025-54381 [CRITICAL] BentoML SSRF Vulnerability in File Upload Processing
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 automatically download files from user-provided URLs without proper validation of internal network addresses.
The framework automatically registers any service endpoint with file-type parameters (`pathlib.Path`, `PIL.Image.Image`) as vulnerable to this attack, making it a framework-wide security issue that affects most real-world ML services handling file uploads. While BentoML implements basic URL scheme validation in the `JSONSerde` path, the `Mult
GHSA
BentoML SSRF Vulnerability in File Upload Processing
ghsa·2025-07-29
CVE-2025-54381 [CRITICAL] CWE-918 BentoML SSRF Vulnerability in File Upload Processing
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 automatically download files from user-provided URLs without proper validation of internal network addresses.
The framework automatically registers any service endpoint with file-type parameters (`pathlib.Path`, `PIL.Image.Image`) as vulnerable to this attack, making it a framework-wide security issue that affects most real-world ML services handling file uploads. While BentoML implements basic URL scheme validation in the `JSONSerde` path, the `Mult
No detection rules found.
No public exploits indexed.
Tenable
How Tenable Found a Way To Bypass a Patch for BentoML’s Server-Side Request Forgery Vulnerability CVE-2025-54381
blogs_tenable·2025-09-17·CVSS 9.9
[CRITICAL] How Tenable Found a Way To Bypass a Patch for BentoML’s Server-Side Request Forgery Vulnerability CVE-2025-54381
## Cloud Exposure
Tenable Cloud Security (CNAPP) Request a demo
Tenable Cloud Vulnerability Management Request a demo
Tenable CIEM Request a demo
Secure your cloud
## Vulnerability Exposure
Tenable Vulnerability Management Try for free
Tenable Security Center Request a demo
Tenable Web App Scanning Try for free
Tenable Patch Management Request a demo
Tenable Enclave Security Request a demo
Tenable Attack Surface Management Request a demo
Tenable Nessus Try for free
## AI Exposure
Tenable AI Exposure Request a demo
## OT/IoT Exposure
Tenable OT Security Request a demo
## Identity Exposure
Tenable Identity Exposure Request a demo
## Business needs
Active Directory
AI Security Posture Management (AI-SPM)
AWS security
Azure security
Cloud Security Posture Man
Tenable
BentoML CVE-2025-54381 (SSRF) Bypass
blogs_tenable·2025-09-08·CVSS 9.9
[CRITICAL] BentoML CVE-2025-54381 (SSRF) Bypass
## Cloud Exposure
Tenable Cloud Security (CNAPP) Request a demo
Tenable Cloud Vulnerability Management Request a demo
Tenable CIEM Request a demo
Secure your cloud
## Vulnerability Exposure
Tenable Vulnerability Management Try for free
Tenable Security Center Request a demo
Tenable Web App Scanning Try for free
Tenable Patch Management Request a demo
Tenable Enclave Security Request a demo
Tenable Attack Surface Management Request a demo
Tenable Nessus Try for free
## AI Exposure
Tenable AI Exposure Request a demo
## OT/IoT Exposure
Tenable OT Security Request a demo
## Identity Exposure
Tenable Identity Exposure Request a demo
## Business needs
Active Directory
AI Security Posture Management (AI-SPM)
AWS security
Azure security
Cloud Security Posture Man
Greynoiseio
NoiseLetter October 2025
blogs_greynoiseio
NoiseLetter October 2025
CVE Disclosure Early Warning Get an early warning when traffic spikes indicate a high likelihood of new disclosures
Compromised Asset Detection Find out immediately if an asset communicates with a malicious IP address
Vulnerability Prioritization Get real-time insight into active exploitation trends to better understand risk and severity
SOC Efficiency Filter out noisy, low priority and false-positive alerts from mass internet scanners
Incident Investigation Add context to incidents to speed the determinations of scope and timelines
Threat Hunting Quickly identify anomalous behavior and enrich your threat hunting campaigns
Why GreyNoise
CVE Disclosure Early Warning Get an early warning when traffic spikes indicate a high likelihood of new disclosures
Compromised Asset Detection Fin
2025-07-29
Published