VulnerabilityPublished 29 Jul 2025Updated 27 Oct 2026

CVE-2025-54381: BentoML SSRF Vulnerability

Affects bentomlSource GCVE Database

Not known to be exploited · 16% EPSS · CVSS 9.9 Critical : upgrade to 1.4.19 as a priority.

Data as of 27 Oct 2026, 18:11 UTC

CVSS 3.1 base score

9.9Critical

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 16.1% chance of exploitation in 30 days – higher than 96% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 1.4.19

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Changed
Confidentiality: High
Integrity: Low
Availability: Low

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Changed: An exploited vulnerability can affect resources beyond the security scope managed by the security authority of the vulnerable component. In this case, the vulnerable component and the impacted component are different and managed by different security authorities.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on the impacted component.
Availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the impacted component are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 29 Jul 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade bentoml to 1.4.19.

Affected software

Product	Affected	Fixed in
PyPIbentoml	Affected >=1.4.0 <1.4.19	Fixed in 1.4.19

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

A patch is available in BentoML version 1.4.19 that addresses this vulnerability by implementing comprehensive URL validation and network restriction checks to block access to internal/private network ranges, localhost, and cloud metadata endpoints. Users should upgrade to version 1.4.19 or later. Until upgraded, users should be aware that the multipart form data handler lacks validation and the JSON handler performs only weak validation, leaving services exposed to SSRF attacks. No other vendor advisory states 'no action required' or 'already mitigated'.

Description

CVE-2025-54381 is a critical Server-Side Request Forgery (SSRF) vulnerability in BentoML's file upload processing system affecting versions >=1.4.0 <1.4.19. It allows unauthenticated remote attackers to make arbitrary HTTP requests from the server to internal network resources, cloud metadata endpoints, or localhost services due to insufficient validation of URLs in multipart form data and JSON request handlers. The vulnerability arises because the framework automatically treats file-type parameters as vulnerable endpoints, and the multipart handler lacks any URL validation. This can lead to credential theft, internal network reconnaissance, and potential exploitation of internal services. A fix is available in version 1.4.19.

Impact

Exploitation of this SSRF vulnerability can lead to unauthorized access to cloud metadata services (AWS, GCP, Azure), enabling credential theft. Attackers can enumerate and interact with internal HTTP services, bypass firewall restrictions, perform internal network reconnaissance, and retrieve sensitive information from HTTP responses. This may also facilitate further exploitation of internal services. The vulnerability has a CVSS 3.1 score of 9.9 (critical), reflecting its high impact on confidentiality, integrity, and availability.

Summary

BentoML versions >=1.4.0 and <1.4.19 contain an SSRF vulnerability in their file upload processing system. The vulnerability exists in the serialization/deserialization handlers for multipart form data and JSON requests, which automatically download files from user-supplied URLs without adequate validation. The multipart handler performs no validation, while the JSON handler only validates URL schemes but does not restrict access to internal or cloud metadata addresses. This design flaw allows attackers to send specially crafted HTTP POST requests with URLs pointing to internal or cloud metadata endpoints, causing the server to make arbitrary HTTP requests. The vulnerability affects most BentoML services that handle file uploads with file-type parameters. The vendor has released a patch in version 1.4.19 that adds comprehensive URL validation and network restrictions to mitigate this issue.

CWE-918Server-Side Request Forgery (SSRF) (opens in a new tab)
Base weaknessCWE Top 25 (2025): #22OWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.
OWASP Cheat Sheets
Server Side Request Forgery Prevention (opens in a new tab)
Unvalidated Redirects and Forwards (opens in a new tab)
Cross Site Scripting Prevention (opens in a new tab)
DOM based XSS Prevention (opens in a new tab)
Authorization (opens in a new tab)
OWASP ASVS 4.0.3
V12.6.1 (opens in a new tab)
V5.2.6 (opens in a new tab)
Attack patterns
Server Side Request Forgery (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 27 Oct 2026, 18:11 UTC

WeaknessesCWE-918

Technical details

References

Community reviews

Related threats