Triton Inference ServerApplication · Nvidia

CVE-2025-23326

HIGH · 7.5 CVSS v3.1 Published 2025-08-06
Fix available
A fix is available. Upgrade to 25.05 or later.
See remediation →
84/100
Remediation priority · High
Remotely reachable No privileges Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

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

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · moderate confidence

NVIDIA Triton Inference Server contains an integer overflow vulnerability in its input handling on both Windows and Linux platforms. An attacker can exploit this by sending a specially crafted input that causes the integer overflow, potentially leading to denial of service.

MitigationApply the NVIDIA security patch when released. In the interim, implement input validation and bounds checking on all numerical inputs processed by the inference server, and restrict network access to the inference endpoint.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
Triton Inference ServerApplication
Affected:< 25.05

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High

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

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify if NVIDIA Triton Inference Server is installed
    Check for the presence of Triton Inference Server by searching for triton executables or containers: which tritonserver, docker ps | grep triton, or look for installation directories like /opt/tritonserver
    Affected if Triton Inference Server is found on the system
  2. Determine the installed version of Triton Inference Server
    Run the tritonserver binary with --version flag, check docker image tags, or look in installation directories for version metadata files
    Affected if The installed version cannot be determined or is below 25.05
  3. Compare installed version to affected range
    Compare the discovered version number to the affected range: any version < 25.05 is vulnerable
    Affected if Installed version is any release prior to 25.05 (e.g., 24.xx, 23.xx, etc.)
  4. Assess network exposure of the inference endpoint
    Check firewall rules, network ACLs, or Kubernetes network policies that control access to Triton server ports (typically 8000 for HTTP, 8001 for gRPC)
    Affected if The Triton Inference Server is reachable over the network by untrusted actors

If Triton Inference Server is installed and the version is below 25.05 with network accessibility, the environment is affected by CVE-2025-23326.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Upgrade available Upgrade to 25.05 or later
Fixed in 25.05
Interim mitigation

Apply the NVIDIA security patch when released. In the interim, implement input validation and bounds checking on all numerical inputs processed by the inference server, and restrict network access to the inference endpoint.

Recommended fix Moderate confidence

Triton Inference Server 25.05

  1. 1. Back up your current Triton Inference Server configuration and any custom models.
  2. 2. Download the fixed Triton Inference Server version 25.05 or later from the official NVIDIANGC catalog or GitHub releases.
  3. 3. Stop the currently running Triton Inference Server service.
  4. 4. Install the new version (25.05) following the standard installation process for your platform (Linux or Windows).
  5. 5. Verify that the service starts successfully and the version number matches 25.05 or later.
  6. 6. Test your inference workflows to confirm normal operation.
  7. 7. Monitor logs for any anomalies following the upgrade.
Caveat Review the 25.05 release notes for any configuration or API changes that may affect existing deployments

Generated from the published advisory — verify against the referenced sources before acting.

Fix this in Triton Inference Server Scoped from the published advisory
  • Consultation3.0 h
  • Implementation6.0 h
  • Testing5.0 h
  • Review / QA3.0 h
17.0 hours of engineering $2,970
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,752.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-23326 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2025-23326 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data