VulnerabilityPublished 24 Mar 2026

CVE-2025-33254: NVIDIA Triton Inference Server · Race Condition

Affects NVIDIA Triton Inference ServerSource CVE Database V5

Compare

Not known to be exploited · CVSS 7.5 High · patch available : patch NVIDIA Triton Inference Server soon.

Data as of 30 Oct 2026, 11:52 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 25% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available

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 24 Mar 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: 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 30 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.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), 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

Affected software

Product	Affected	Fixed in
NVIDIATriton Inference Server	Affected =All versions prior to 26.01	Fixed in–

AI-suggested

Upgrade to NVIDIA Triton Inference Server version 26.01 or later as soon as the patch is available to eliminate the race condition vulnerability.
Until patching is possible, restrict network access to the Triton server by implementing strict firewall rules and network segmentation to limit exposure to untrusted sources.
Employ runtime monitoring and anomaly detection to identify unusual server behavior indicative of race condition exploitation attempts, such as unexpected crashes or service interruptions.
Review and harden concurrent execution configurations and resource access policies within the deployment environment to minimize race condition risks.
Conduct thorough testing of AI inference workloads post-patching to ensure stability and performance are maintained.
Maintain up-to-date incident response plans that include procedures for handling denial of service events affecting AI infrastructure.
Engage with NVIDIA security advisories and community forums for updates and best practices related to Triton server security.

Description

NVIDIA Triton Inference Server contains a vulnerability where an attacker may cause internal state corruption. A successful exploit of this vulnerability may lead to a denial of service.

Impact

The primary impact of CVE-2025-33254 is denial of service, which can disrupt AI inference workloads dependent on the NVIDIA Triton Inference Server. Organizations utilizing this server for critical AI applications—such as autonomous systems, real-time analytics, or cloud-based AI services—may experience service outages, leading to operational downtime and potential financial losses. Although confidentiality and integrity are not directly compromised, the availability disruption can affect dependent systems and users, potentially cascading into broader business impacts. The vulnerability’s remote exploitability without authentication increases the attack surface, especially in environments where the Triton server is exposed to untrusted networks. Given the growing adoption of AI inference platforms globally, the threat could affect a wide range of sectors including technology, automotive, healthcare, and cloud service providers. The absence of known exploits in the wild currently limits immediate risk, but the vulnerability’s characteristics make it a high-priority patching candidate to prevent future exploitation.

CWE-362Concurrent Execution using Shared Resource with Improper Synchronization (Race Condition) (opens in a new tab)
Class weaknessLikelihood of exploit: MediumOWASP Top 10 A06:2025: Insecure Design (opens in a new tab)
The product contains a concurrent code sequence that requires temporary, exclusive access to a shared resource, but a timing window exists in which the shared resource can be modified by another code sequence operating concurrently.
Architecture and Design
In languages that support it, use synchronization primitives. Only wrap these around critical code to minimize the impact on performance.
Architecture and Design
Use thread-safe capabilities such as the data access abstraction in Spring.
Architecture and Design
Minimize the usage of shared resources in order to remove as much complexity as possible from the control flow and to reduce the likelihood of unexpected conditions occurring.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Secure Design Principles (opens in a new tab)
OWASP ASVS 4.0.3
V1.11.2 (opens in a new tab)
Attack patterns
Leveraging Time-of-Check and Time-of-Use (TOCTOU) Race Conditions (opens in a new tab)
Leveraging Race Conditions (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 24 Mar 2026, 20:48 UTC

WeaknessesCWE-362

Technical details

References

Community reviews

Related threats