dbcve.org
Triton Inference ServerApplication · Nvidia

CVE-2025-23329

HIGH · 7.5 CVSS v3.1 Published 2025-09-17
Fix available
A fix is available. Upgrade to 25.08 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 memory corruption by identifying and accessing the shared memory region used by the Python backend. 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 a vulnerability in its shared memory handling for the Python backend. An attacker who can identify the shared memory region used by the Python backend can access it directly, causing memory corruption. This leads to denial of service due to the ability to read/write to this inter-process communication channel.

MitigationImplement strict access controls on shared memory segments, restrict file system permissions on /dev/shm and temporary directories, and apply NVIDIA's security patch when available. Consider network segmentation to limit attacker ability to identify shared memory regions.

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:< 25.08

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 Triton Inference Server version
    Run 'tritonserver --version' or check the installed package version via package manager (e.g., 'pip show tritoninferenceserver' or 'apt list --installed | grep triton')
    Affected if Version is below 25.08 (or version cannot be determined and Triton is present)
  2. Determine if Python backend is enabled
    Review Triton configuration files (typically in /opt/tritonserver/models or specified via --model-repository flag) and check for python model definitions (.py files or config.pbtxt with backend: python)
    Affected if Python backend is configured and loaded in the Triton instance
  3. Inspect shared memory permissions on /dev/shm
    Run 'ls -la /dev/shm' and check for world-writable shared memory segments. Also run 'mount | grep shm' to review shm mount options
    Affected if Shared memory is world-writable or lacks restrictive access controls (e.g., no 'nosuid' 'nodev' 'noexec' options)
  4. Check file system permissions on model repository
    Examine the model repository directory permissions and ownership. Look for shared memory files or socket files in the model directories and temporary locations (check /tmp, /var/tmp, model paths)
    Affected if Model directories or temporary storage used by Python backend allow unauthorized access

If Triton Inference Server version is below 25.08, the Python backend is active, and shared memory or related file system locations have weak permissions, the environment is vulnerable to this shared memory access flaw.

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 25.08 or later
Fixed in 25.08
Interim mitigation

Implement strict access controls on shared memory segments, restrict file system permissions on /dev/shm and temporary directories, and apply NVIDIA's security patch when available. Consider network segmentation to limit attacker ability to identify shared memory regions.

Recommended fix High confidence

Triton Inference Server 25.08 or later

  1. 1. Backup any existing Triton Inference Server configurations and data
  2. 2. Stop the currently running Triton Inference Server service
  3. 3. Download Triton Inference Server version 25.08 or later from NVIDIA's official repository or container registry
  4. 4. For containerized deployments: Pull the new container image (e.g., nvcr.io/nvidia/tritonserver:25.08-py3)
  5. 5. For bare-metal installations: Install the new version using the appropriate package manager or binary for your OS
  6. 6. Verify the installation by checking the Triton server version (tritonserver --version)
  7. 7. Restore configurations and start the Triton Inference Server service
  8. 8. Validate that the Python backend is functioning correctly with the new version

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

Fix this in Triton Inference Server Scoped from the published advisory
  • Consultation6.0 h
  • Implementation12.0 h
  • Testing8.0 h
  • Review / QA4.0 h
30.0 hours of engineering $5,280
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $8,448.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-23329 — 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-2025-23329 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