dbcve.org
Triton Inference ServerApplication · Nvidia

CVE-2025-23321

HIGH · 7.5 CVSS v3.1 Published 2025-08-06
Fix available
A fix is available. Upgrade to 25.07 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 a user could cause a divide by zero issue by issuing an invalid request. 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 · high confidence

NVIDIA Triton Inference Server contains a divide-by-zero vulnerability in its request handling logic. An attacker can trigger this by issuing a specially crafted invalid request, causing the server to crash and resulting in denial of service.

MitigationApply the vendor patch or update to a fixed version of Triton Inference Server that properly validates input and handles the division operation safely.

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:< 25.07

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. Confirm Triton Inference Server is installed
    Check for Triton Inference Server processes running on the system. Common commands: 'ps aux | grep tritonserver' or 'docker ps' if running as container. Also check common installation paths like /opt/tritonserver or /opt/nvidia/tritonserver.
    Affected if Triton Inference Server process is found running on the system
  2. Identify the installed version
    Run the Triton server binary with --version flag: 'tritonserver --version' or check the container image tag. If using a package manager, query with: 'dpkg -l | grep triton' (Debian) or 'rpm -qi triton-server' (RHEL).
    Affected if Version returned is less than 25.07 (e.g., 25.06, 25.05, 24.x, etc.)
  3. Verify the server receives external requests
    Check Triton server configuration for enabled endpoints and network binding. Review config.pbtxt for 'port' and 'http_address' settings. Check firewall rules to confirm external access is permitted.
    Affected if Server has exposed HTTP/gRPC endpoints accepting requests from untrusted sources
  4. Check for recent crash logs
    Review server logs for divide-by-zero errors or sudden crashes around request handling. Common log locations: /var/log/tritonserver/, or docker logs. Search for 'Floating point exception' or 'divide by zero' in logs.
    Affected if Recent crashes logged with arithmetic exception errors, especially when handling malformed requests

If Triton Inference Server is installed and the version is below 25.07 with exposed endpoints, the environment is likely affected by this divide-by-zero vulnerability.

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 25.07 or later
Fixed in 25.07
Interim mitigation

Apply the vendor patch or update to a fixed version of Triton Inference Server that properly validates input and handles the division operation safely.

Recommended fix High confidence

Triton Inference Server 25.07

  1. 1. Back up your current Triton Inference Server configuration and data directories
  2. 2. Stop the Triton Inference Server service
  3. 3. Download Triton Inference Server version 25.07 or later from NVIDIA's official repository
  4. 4. Install the new version following NVIDIA's installation documentation for your platform (Windows or Linux)
  5. 5. Restore your backed-up configuration if needed
  6. 6. Start the Triton Inference Server service
  7. 7. Verify the server is running correctly and test that the divide-by-zero vulnerability is no longer present
Caveat Review NVIDIA's 25.07 release notes for any configuration or API changes before upgrading in production environments

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

Fix this in Triton Inference Server Scoped from the published advisory
  • Consultation4.0 h
  • Implementation4.0 h
  • Testing4.0 h
  • Review / QA2.0 h
14.0 hours of engineering $2,480
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,968.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-23321 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

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-2025-23321 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