CVE-2025-23336
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 · uneditedNVIDIA Triton Inference Server for Windows and Linux contains a vulnerability where an attacker could cause a denial of service by loading a misconfigured model. 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 confidenceNVIDIA Triton Inference Server contains a denial-of-service vulnerability where loading a specially crafted or misconfigured model can cause the service to become unavailable. The vulnerability stems from insufficient validation of model configuration during the loading process, allowing a remote attacker to trigger a crash or resource exhaustion by presenting a malformed model.
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< 25.08CVSS 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 checksWork through these to decide whether this CVE applies to you.
-
Identify the installed Triton Inference Server versionRun 'tritonserver --version' or check the Docker image tag if running in a container. If installed via package manager, check with 'dpkg -l' or 'rpm -q' for triton inference server packages.Affected if The installed version is older than 25.08, meaning it is vulnerable to malformed model configuration validation issues.
-
Verify if model repository is configured and accessibleCheck the Triton server configuration for model repository paths (typically set via --model-repository flag or in config.pbtxt). Examine if the model repository directory is writable or exposed to untrusted users.Affected if A model repository is configured and the directory has write permissions for non-administrative users, allowing potential injection of malformed model configurations.
-
Confirm network exposure of the Triton inference endpointReview network binding configuration (--http-address flag, default is 0.0.0.0:8000). Check firewall rules and container network settings to determine if the Triton HTTP/gRPC ports are accessible from untrusted networks.Affected if The Triton server HTTP or gRPC ports are exposed to untrusted network segments, allowing remote attackers to submit model loading requests.
-
Examine access control on model loading APIsReview Triton server configuration for authentication settings. Check if the model loading endpoints (/v2/repository/models/... POST/delete) are protected by authentication or restricted to localhost/trusted IPs.Affected if Model loading APIs lack authentication or IP-based restrictions, permitting any caller to load arbitrary model configurations into the server.
The environment is affected if Triton Inference Server version is below 25.08 AND the model loading interface is accessible to untrusted users, as the vulnerability can be triggered by a specially crafted model configuration submitted through these exposed APIs.
Generated from the published advisory. Verify against your own configuration.
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 · scoped25.08
Apply NVIDIA's security patch for Triton Inference Server when available. Until then, restrict model loading permissions to trusted administrators only and implement network access controls to limit exposure.
Triton Inference Server 25.08
- 1. Backup your current Triton Inference Server configuration and model repository.
- 2. Stop the running Triton Inference Server instance.
- 3. Download Triton Inference Server version 25.08 or later from the NVIDIA NGC catalog or official download渠道.
- 4. Install the new version following the standard installation process for your platform (Windows or Linux).
- 5. Verify the installation by checking the Triton server version.
- 6. Restart the Triton Inference Server service.
- 7. Test that model loading works correctly with your models.
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation2.0 h
- Implementation4.0 h
- Testing8.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,288.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2025-23336 — 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 sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2025-23336 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
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.
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.
- 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