CVE-2025-23328VulnerabilityPublished 17 Sep 2025

CVE-2025-23328: NVIDIA Triton Inference Server · Out-of-bounds Write

Affects NVIDIA Triton Inference ServerSource CVE Database V5

Not known to be exploited · CVSS 7.5 High : upgrade to 25.08 soon.

Data as of 25 Oct 2026, 19:02 UTC

CVSS 3.1 base score

7.5High

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

EPSS: 0.3% chance of exploitation in 30 days – higher than 32% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 25.08

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

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

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: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: None: There is no loss of confidentiality within the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: High: There is total loss of availability, resulting in the attacker being able to fully deny access to resources in the impacted component; this loss is either sustained (while the attacker continues to deliver the attack) or persistent (the condition persists even after the attack has completed). Alternatively, the attacker has the ability to deny some availability, but the loss of availability presents a direct, serious consequence to the impacted component (e.g., the attacker cannot disrupt existing connections, but can prevent new connections; the attacker can repeatedly exploit a vulnerability that, in each instance of a successful attack, leaks a only small amount of memory, but after repeated exploitation causes a service to become completely unavailable).

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 17 Sep 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 2026-10-25.

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 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 NVIDIA Triton Inference Server to 25.08.

Affected software

Product	Affected	Fixed in
NVIDIA Triton Inference Server	Affected <25.08	Fixed in 25.08

AI-suggested

To mitigate this vulnerability effectively, European organizations should prioritize upgrading NVIDIA Triton Inference Server to version 25.08 or later as soon as the patch becomes available. Until then, organizations should implement network-level protections such as firewall rules and intrusion prevention systems to restrict access to Triton Inference Server endpoints, limiting exposure to trusted networks and IP addresses only. Employing network segmentation to isolate AI inference servers from general-purpose networks can reduce the attack surface. Monitoring and logging network traffic to detect anomalous or malformed inputs targeting the inference server is also recommended. Additionally, organizations should conduct thorough input validation and sanitization at the application layer where possible, and consider deploying runtime application self-protection (RASP) or endpoint detection and response (EDR) solutions to identify and mitigate exploitation attempts. Regular vulnerability scanning and penetration testing focused on AI infrastructure will help identify residual risks. Finally, maintaining an incident response plan that includes AI infrastructure components will ensure rapid containment and recovery in case of an attack.

Description

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability where an attacker could cause an out-of-bounds write through a specially crafted input. A successful exploit of this vulnerability might lead to denial of service.

Impact

For European organizations, the impact of CVE-2025-23328 can be substantial, particularly for those relying on NVIDIA Triton Inference Server for AI-driven applications such as healthcare diagnostics, autonomous systems, financial modeling, and industrial automation. A successful exploitation could lead to service outages, disrupting critical AI inference workloads and potentially causing cascading effects on business operations and service delivery. The denial of service could affect cloud service providers hosting AI workloads, research institutions, and enterprises integrating AI into their infrastructure. While the vulnerability does not directly compromise data confidentiality or integrity, the loss of availability can result in financial losses, reputational damage, and operational delays. Additionally, organizations in sectors with stringent uptime requirements, such as healthcare and transportation, may face regulatory and compliance challenges if AI services are interrupted. The fact that exploitation requires no authentication or user interaction increases the risk profile, as attackers can remotely target exposed Triton servers without prior access.

CWE-787Out-of-bounds Write (opens in a new tab)
Base weaknessLikelihood of exploit: HighCWE Top 25 (2025): #5
The product writes data past the end, or before the beginning, of the intended buffer.
Requirements · Language Selection
Use a language that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
Architecture and Design · Libraries or Frameworks
Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
Operation · Build and Compilation · Environment Hardening
Use automatic buffer overflow detection mechanisms that are offered by certain compilers or compiler extensions. Examples include: the Microsoft Visual Studio /GS flag, Fedora/Red Hat FORTIFY_SOURCE GCC flag, StackGuard, and ProPolice, which provide various mechanisms including canary-based detection and range/index…
OWASP Cheat Sheets
XML Security (opens in a new tab)
Mass Assignment (opens in a new tab)
OWASP ASVS 4.0.3
V13.3.1 (opens in a new tab)
V5.1.4 (opens in a new tab)
V5.1.3 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

nvidia.custhelp.com/app/answers/detail/a_id/5691 (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 25 Sep 2025, 00:45 UTC

WeaknessesCWE-787

Technical details

References

Community reviews

Related threats