VulnerabilityPublished 6 Aug 2025

CVE-2025-23322: NVIDIA Triton Inference Server · Double Free

Affects NVIDIA Triton Inference ServerSource CVE Database V5

Not known to be exploited · CVSS 7.5 High : upgrade to 25.06 soon.

Data as of 26 Oct 2026, 12:55 UTC

CVSS 3.1 base score

7.5High

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

EPSS: 0.5% chance of exploitation in 30 days – higher than 47% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 25.06

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 25.06.

Affected software

Product	Affected	Fixed in
NVIDIA Triton Inference Server	Affected <25.06	Fixed in 25.06

AI-suggested

To mitigate this vulnerability, European organizations should prioritize upgrading to NVIDIA Triton Inference Server version 25.06 or later as soon as it becomes available, as this version addresses the double free issue. If you cannot patch yet, organizations should implement network-level protections such as firewall rules and intrusion prevention systems to restrict access to the Triton server endpoints, limiting exposure to untrusted networks. Monitoring and logging of inference server activity should be enhanced to detect abnormal request patterns that might trigger the vulnerability. Employing rate limiting on incoming requests can reduce the likelihood of multiple simultaneous cancellations that cause the double free. Additionally, deploying Triton servers within isolated network segments or behind API gateways can add layers of defense. Organizations should also prepare incident response plans to quickly recover from potential denial of service events, including automated restarts and failover mechanisms to maintain service availability. Close coordination with NVIDIA support channels is recommended to receive timely updates and guidance.

Description

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability where multiple requests could cause a double free when a stream is cancelled before it is processed. A successful exploit of this vulnerability might lead to denial of service.

Impact

For European organizations, the impact of this vulnerability could be substantial, particularly for those relying on NVIDIA Triton Inference Server to power AI-driven applications in sectors such as automotive, healthcare, finance, and manufacturing. A denial of service could interrupt critical AI inference tasks, leading to operational downtime, degraded service quality, and potential financial losses. In healthcare, for example, AI models used for diagnostics or patient monitoring could be disrupted, affecting patient care. In finance, real-time fraud detection systems might be impaired. Additionally, organizations providing AI-as-a-service or cloud-based AI solutions could face customer dissatisfaction and reputational damage. The vulnerability does not directly compromise confidentiality or integrity, but the availability impact alone can have cascading effects on business continuity and compliance with service-level agreements (SLAs). Given the increasing adoption of AI technologies across Europe, the risk of operational disruption is non-trivial, especially in environments with high dependency on automated inference pipelines.

CWE-415Double Free (opens in a new tab)
Variant weaknessLikelihood of exploit: High
The product calls free() twice on the same memory address.
Architecture and Design
Choose a language that provides automatic memory management.
Implementation
Ensure that each allocation is freed only once. After freeing a chunk, set the pointer to NULL to ensure the pointer cannot be freed again. In complicated error conditions, be sure that clean-up routines respect the state of allocation properly.
Implementation
Use a static analysis tool to find double free instances.
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

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 6 Aug 2025, 13:18 UTC

WeaknessesCWE-415

Technical details

References

Community reviews

Related threats