Triton Inference ServerApplication · Nvidia

CVE-2024-0095

HIGH · 7.2 CVSS v3.1 Published 2024-06-13
Fix available
A fix is available. Upgrade to 24.05 or later.
See remediation →
78/100
Remediation priority · High
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 a user can inject forged logs and executable commands by injecting arbitrary data as a new log entry. A successful exploit of this vulnerability might 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 log injection vulnerability where user-supplied input is not properly sanitized before being written to logs. An attacker can inject arbitrary data as new log entries, potentially including executable commands that could be interpreted when logs are viewed or processed by other systems. This can lead to code execution, denial of service, privilege escalation, information disclosure, or data tampering.

MitigationImplement strict input validation and sanitization for all user-supplied data before logging. Use parameterized logging APIs or escape special characters to prevent log injection and command execution via log entries.

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:>= 20.10, < 24.05

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

CVSS:3.1/AV:N/AC:L/PR:H/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
    Run 'tritonserver --version' or check the container image tag if running via Docker. If installed via pip, run 'pip show tritoninferenceserver' or check the installed package version.
    Affected if The installed version is >= 20.10 and < 24.05
  2. Verify the version is within affected range
    Compare the identified version number against the vulnerable range: 20.10 through 24.04 (inclusive). Versions 24.05 and later are patched.
    Affected if The version falls within >= 20.10 and < 24.05
  3. Confirm the service is accessible to untrusted users
    Check if Triton Inference Server HTTP/REST or gRPC endpoints are exposed to network or untrusted users. Review service binding configuration ('--http-port', '--grpc-port', '--metrics-port' flags or config).
    Affected if The service accepts user requests from untrusted sources, providing attack surface for log injection
  4. Review custom model repository paths
    If using custom model repositories, verify whether user-controlled model names or metadata could be passed to the server, as model names may appear in logs.
    Affected if User-supplied model names or data can reach the server and be logged without sanitization

You are affected if Triton Inference Server version is 20.10 or higher but lower than 24.05 and accepts user input that gets logged.

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 24.05 or later
Fixed in 24.05
Interim mitigation

Implement strict input validation and sanitization for all user-supplied data before logging. Use parameterized logging APIs or escape special characters to prevent log injection and command execution via log entries.

Recommended fix High confidence

Triton Inference Server >= 24.05

  1. 1. Back up your current Triton Inference Server configuration and model repository
  2. 2. Stop the Triton Inference Server service
  3. 3. Upgrade Triton Inference Server to version 24.05 or later
  4. 4. Verify the upgrade by checking the server version: `tritonserver --version`
  5. 5. Test that models load correctly and inference works as expected
  6. 6. Monitor logs to confirm log injection vulnerability is resolved
Caveat Review NVIDIA Triton Inference Server 24.05 release notes for any breaking changes, especially regarding API compatibility, model format support, and configuration syntax

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 / QA4.0 h
22.0 hours of engineering $3,860
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $6,176.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2024-0095 — 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-2024-0095 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