VulnerabilityPublished 6 Aug 2025

CVE-2025-23325: NVIDIA Triton Inference Server · Uncontrolled Recursion

Affects NVIDIA Triton Inference ServerSource CVE Database V5

Not known to be exploited · CVSS 7.5 High : upgrade to 25.05 soon.

Data as of 26 Oct 2026, 10:12 UTC

CVSS 3.1 base score

7.5High

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

EPSS: 0.4% chance of exploitation in 30 days – higher than 41% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 25.05

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 6 Aug 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 NVIDIA Triton Inference Server to 25.05.

Affected software

Product	Affected	Fixed in
NVIDIA Triton Inference Server	Affected <25.05	Fixed in 25.05

AI-suggested

To mitigate this vulnerability, European organizations should prioritize upgrading NVIDIA Triton Inference Server to version 25.05 or later once the patch is released. Until then, organizations should implement network-level protections such as restricting access to the inference server to trusted internal networks and using firewalls or VPNs to limit exposure. Deploying Web Application Firewalls (WAFs) or Intrusion Prevention Systems (IPS) with custom rules to detect and block anomalous recursive input patterns may help reduce risk. Monitoring server logs and resource usage for unusual spikes indicative of recursion attacks is advisable. Additionally, organizations should conduct thorough security assessments of their AI infrastructure, including penetration testing focused on input validation and resource exhaustion scenarios. Implementing rate limiting and input validation at the application layer can further reduce the attack surface. Finally, maintaining an incident response plan that includes AI infrastructure components will help organizations respond swiftly to potential exploitation attempts.

Description

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

Impact

For European organizations, the impact of this vulnerability can be substantial, especially for those relying on NVIDIA Triton Inference Server to deploy AI and machine learning models in production environments. Industries such as automotive, healthcare, finance, and manufacturing increasingly use AI inference servers for critical decision-making and automation. A successful DoS attack could disrupt business operations, cause downtime in AI-driven services, and potentially lead to financial losses and reputational damage. Given the remote and unauthenticated nature of the exploit, attackers could launch attacks from anywhere, increasing the threat landscape. Additionally, organizations with AI infrastructure exposed to the internet or insufficiently segmented internal networks are at higher risk. The disruption of AI inference services might also affect compliance with data processing regulations if service availability is mandated. Therefore, the vulnerability poses a direct threat to operational continuity and service reliability within European enterprises leveraging NVIDIA’s AI inference technology.

CWE-674Uncontrolled Recursion (opens in a new tab)
Class weakness
The product does not properly control the amount of recursion that takes place, consuming excessive resources, such as allocated memory or the program stack.
Implementation
Ensure that an end condition will be reached under all logic conditions. The end condition may include checking against the depth of recursion and exiting with an error if the recursion goes too deep. The complexity of the end condition contributes to the effectiveness of this action.
Implementation
Increase the stack size.
Attack patterns
Serialized Data with Nested Payloads (opens in a new tab)
Oversized Serialized Data Payloads (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 6 Aug 2025, 13:18 UTC

WeaknessesCWE-674

Technical details

References

Community reviews

Related threats