dbcve.org
Triton Inference ServerApplication · Nvidia

CVE-2023-31036

HIGH · 8.8 CVSS v3.1 Published 2024-01-12
Fix available
A fix is available. Upgrade to 2.40 or later.
See remediation →
94/100
Remediation priority · Urgent
Remotely reachable 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 Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal. A successful exploit of this vulnerability may lead to code execution, denial of service, escalation of privileges, information disclosure, and data tampering.

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 path traversal vulnerability when the non-default --model-control explicit option is enabled. An attacker can exploit the model load API by providing paths with relative traversal sequences (e.g., ../../../) to access files outside the intended model directory. This can lead to code execution, denial of service, privilege escalation, information disclosure, or data tampering.

MitigationAvoid using --model-control explicit in production deployments unless strictly required; if needed, implement strict path validation to prevent traversal sequences in model load requests and restrict API access via authentication and network controls.

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:< 2.40

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
Low
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/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 installation
    Locate the Triton server binary or container. Common paths: /opt/tritonserver, /usr/local/bin/tritonserver, or check running containers with 'docker ps'. Query the version using '--version' flag or check the image tag.
    Affected if Triton Inference Server is not installed or version cannot be determined
  2. Verify installed version
    Run 'tritonserver --version' or inspect the container image tag. Compare the version number against the affected range: versions prior to 2.40.
    Affected if Installed version is lower than 2.40 (e.g., 2.38.x, 2.39.x)
  3. Check if model-control explicit is enabled
    Inspect the Triton server startup command or configuration. For containers, run 'docker inspect <container>' and review the Cmd or Args section. Look for '--model-control explicit' in the launch arguments.
    Affected if The --model-control explicit flag is present in the server startup parameters
  4. Confirm model load API exposure
    Verify the Triton HTTP/REST or gRPC API endpoint is accessible. Check network configuration or firewall rules. The vulnerability is exploitable via the model load API endpoint when explicit mode is enabled.
    Affected if The Triton model load API is network-accessible without strict authentication

You are affected if Triton Inference Server version is below 2.40 AND the --model-control explicit option is enabled, exposing the model load API to path traversal attacks.

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 2.40 or later
Fixed in 2.40
Interim mitigation

Avoid using --model-control explicit in production deployments unless strictly required; if needed, implement strict path validation to prevent traversal sequences in model load requests and restrict API access via authentication and network controls.

Recommended fix High confidence

Triton Inference Server 2.40 or later

  1. 1. Identify the current Triton Inference Server version in use (e.g., check via Docker image tag or installed package version)
  2. 2. Back up all model repositories and configuration files
  3. 3. Stop the Triton Inference Server service
  4. 4. Upgrade Triton Inference Server to version 2.40 or later
  5. 5. If using the --model-control explicit option, verify that the upgrade resolves the path traversal vulnerability
  6. 6. Restart the Triton Inference Server service
  7. 7. Test model loading functionality to confirm normal operation

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

Fix this in Triton Inference Server Scoped from the published advisory
  • Consultation2.0 h
  • Implementation4.0 h
  • Testing3.0 h
  • Review / QA2.0 h
11.0 hours of engineering $1,930
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,088.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2023-31036 — 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-2023-31036 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