Triton Inference ServerApplication · Nvidia

CVE-2025-23322

HIGH · 7.5 CVSS v3.1 Published 2025-08-06
Fix available
A fix is available. Upgrade to 25.06 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 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.

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 double free vulnerability in its streaming request handling. When a stream is cancelled before processing and multiple requests are involved, the same memory is freed twice, leading to undefined behavior and potential denial of service.

MitigationApply vendor-supplied patches when available. In the interim, implement rate limiting and request validation to reduce the likelihood of triggering the race condition during stream cancellation.

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:< 25.06

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 NVIDIA Triton Inference Server is installed
    Check for Triton installation by reviewing common install locations or running commands like 'tritonserver --version' or checking container images if running in containers
    Affected if Triton Inference Server is present in the environment
  2. Identify the installed Triton version
    Run 'tritonserver --version' or check the version through the container image tag, API endpoint '/v2/health/ready', or package management system
    Affected if The installed version is older than 25.06 (e.g., 25.05, 25.04, earlier releases)
  3. Determine if streaming inference is in use
    Review client code and configuration for use of gRPC streaming (InferenceServerGrpcSt Service) or HTTP streaming endpoints, check if any models are configured with streaming enabled
    Affected if Streaming inference endpoints are actively used by clients or configured in the server
  4. Review server logs for crash or memory error indicators
    Examine Triton server logs (console output or configured log files) for messages containing 'double free', 'corruption', 'abort', 'segmentation fault', or 'malloc error' especially during stream cancellation events
    Affected if Logs contain double-free errors, memory corruption warnings, or crashes coinciding with stream cancellation attempts
  5. Check for untrusted client access to streaming endpoints
    Identify if streaming inference endpoints are exposed to untrusted or external clients who could cancel streams, review network access controls and authentication on gRPC/HTTP streaming ports
    Affected if Streaming endpoints are accessible to clients that could trigger race conditions through stream cancellation

The environment is affected if Triton Inference Server version is below 25.06 AND streaming inference is enabled and accessible, particularly if clients can cancel streams during multi-request processing.

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 25.06 or later
Fixed in 25.06
Interim mitigation

Apply vendor-supplied patches when available. In the interim, implement rate limiting and request validation to reduce the likelihood of triggering the race condition during stream cancellation.

Recommended fix High confidence

Triton Inference Server 25.06

  1. Upgrade NVIDIA Triton Inference Server to version 25.06 or later
  2. After upgrading, verify that the server starts successfully and handles stream cancellation without crashing

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 / QA2.0 h
20.0 hours of engineering $3,500
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $5,600.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-23322 — 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-2025-23322 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