VulnerabilityPublished 3 Dec 2025

CVE-2025-33201: NVIDIA Triton Inference Server · Unchecked Error Condition

Affects NVIDIA Triton Inference ServerSource CVE Database V5

Not known to be exploited · CVSS 7.5 High : upgrade to 25.10 soon.

Data as of 26 Oct 2026, 11:42 UTC

CVSS 3.1 base score

7.5High

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

EPSS: 0.9% chance of exploitation in 30 days – higher than 60% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 25.10

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 3 Dec 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 25.10.

Affected software

Product	Affected	Fixed in
NVIDIA Triton Inference Server	Affected <25.10	Fixed in 25.10

AI-suggested

To mitigate CVE-2025-33201, organizations should prioritize upgrading NVIDIA Triton Inference Server to version r25.10 or later once the patch is released. Until then, network-level controls should be implemented to restrict the size of payloads accepted by the server, such as configuring firewalls or application-layer gateways to enforce maximum request sizes. Deploying rate limiting and anomaly detection can help identify and block unusual traffic patterns indicative of exploitation attempts. It is also advisable to isolate Triton servers within segmented network zones with limited exposure to untrusted networks. Monitoring server logs and performance metrics for signs of crashes or resource exhaustion can provide early warning of attempted exploitation. Additionally, organizations should review and harden input validation mechanisms in any custom integrations with Triton. Regular vulnerability scanning and penetration testing focused on AI infrastructure can help detect similar issues proactively. Finally, maintaining an incident response plan that includes AI service disruptions will improve resilience against denial of service attacks.

Description

NVIDIA Triton Inference Server contains a vulnerability where an attacker may cause an improper check for unusual or exceptional conditions issue by sending extra large payloads. A successful exploit of this vulnerability may lead to denial of service.

Impact

For European organizations, the primary impact of CVE-2025-33201 is the potential for denial of service attacks against AI inference infrastructure. Organizations relying on NVIDIA Triton Inference Server for critical AI workloads—such as autonomous systems, financial services, healthcare diagnostics, or industrial automation—may experience service outages or degraded performance. This can disrupt business operations, cause financial losses, and damage reputation. Given the increasing adoption of AI technologies across Europe, especially in countries with strong technology sectors, the risk of operational disruption is significant. Additionally, denial of service conditions could be leveraged as part of multi-stage attacks to distract or delay incident response. The vulnerability does not directly expose data confidentiality or integrity but impacts system availability, which is critical for real-time AI applications. Organizations with exposed Triton servers on public or semi-public networks are at heightened risk. The absence of known exploits currently provides a window for proactive mitigation before active attacks emerge.

CWE-754Improper Check for Unusual or Exceptional Conditions (opens in a new tab)
Class weaknessLikelihood of exploit: MediumOWASP Top 10 A10:2025: Mishandling of Exceptional Conditions (opens in a new tab)
The product does not check or incorrectly checks for unusual or exceptional conditions that are not expected to occur frequently during day to day operation of the product.
Requirements · Language Selection
Use a language that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
Implementation
Check the results of all functions that return a value and verify that the value is expected.
Implementation
If using exception handling, catch and throw specific exceptions instead of overly-general exceptions (CWE-396, CWE-397). Catch and handle exceptions as locally as possible so that exceptions do not propagate too far up the call stack (CWE-705). Avoid unchecked or uncaught exceptions where feasible (CWE-248).
OWASP Cheat Sheets
Logging (opens in a new tab)
Error Handling (opens in a new tab)
OWASP ASVS 4.0.3
V11.1.7 (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 10 Dec 2025, 18:36 UTC

WeaknessesCWE-754

Technical details

References

Community reviews

Related threats