Triton Inference ServerApplication · Nvidia

CVE-2026-24146

HIGH · 7.5 CVSS v3.1 Published 2026-04-07
Fix available
A fix is available. Upgrade to 26.02 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 contains a vulnerability where insufficient input validation and a large number of outputs could cause a server crash. 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 fails to properly validate inputs and bounds-check the number of outputs, allowing attackers to trigger excessive outputs that crash the server. This is a denial-of-service vulnerability stemming from missing validation in the inference request handling path.

MitigationImplement rigorous input validation on inference requests to enforce output limits, add bounds checking before allocating or processing output tensors, and configure appropriate resource limits on the inference server.

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:< 26.02

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. Check Triton Inference Server version
    Run 'tritonserver --version' from the command line, or query the server's metrics API at /metrics endpoint and look for the 'triton_server_version' metric. If running in a container, inspect the image tag.
    Affected if Version is lower than 26.02
  2. Verify inference endpoint exposure
    Identify network listeners on ports 8000 (REST API) and 8001 (gRPC). Review firewall rules, network policies, or reverse proxy configurations to determine if these endpoints are accessible from untrusted sources.
    Affected if Inference endpoints are exposed to untrusted or public networks without access controls
  3. Inspect model output configuration
    Examine the config.pbtxt file for each deployed model in the model repository. Look for the 'max_output_size' parameter in the output configuration section. Also check the main server configuration for any global output limits.
    Affected if max_output_size parameter is not set in model configurations and no global output limits are defined

Environment is affected if Triton Inference Server version is below 26.02 and the server accepts inference requests from untrusted sources without configured output limits.

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 26.02 or later
Fixed in 26.02
Interim mitigation

Implement rigorous input validation on inference requests to enforce output limits, add bounds checking before allocating or processing output tensors, and configure appropriate resource limits on the inference server.

Recommended fix Moderate confidence

26.02

  1. 1. Identify the current version of Triton Inference Server by checking the container image tag or running the server with --version flag
  2. 2. Stop the Triton Inference Server service
  3. 3. Upgrade to Triton Inference Server version 26.02 or later by pulling the updated container image (e.g., nvcr.io/nvidia/tritonserver:26.02-py3)
  4. 4. Restart the Triton Inference Server with the same configuration
  5. 5. Verify the server starts successfully and responds to requests

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
  • Implementation8.0 h
  • Testing6.0 h
  • Review / QA3.0 h
21.0 hours of engineering $3,680
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $5,888.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-24146 — 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-2026-24146 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