dbcve.org
TensorrtApplication · Nvidia

CVE-2026-24272

HIGH · 7.8 CVSS v3.1 Published 2026-07-14
Fix available
A fix is available. Upgrade to 11.0 or later.
See remediation →
81/100
Remediation priority · High
No privileges 5 weeks old

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 TensorRT contains a vulnerability where an attacker might cause an overflow to a heap-based buffer. A successful exploit of this vulnerability might lead to code execution.

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 TensorRT contains a heap-based buffer overflow vulnerability that allows an attacker to overflow a heap-allocated buffer. Successful exploitation could enable arbitrary code execution on the affected system.

MitigationApply the NVIDIA TensorRT security patch or update to a patched version once available. If immediate patching is not feasible, restrict network access to systems running TensorRT and ensure proper input validation is performed on model inputs.

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
TensorrtApplication
Affected:< 11.0

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
Local
Complexity
Low
Privileges
None
User interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/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 if TensorRT is installed
    Run 'dpkg -l | grep tensorrt' on Debian-based systems, or 'rpm -qa | grep tensorrt' on RHEL-based systems. On Windows, check for 'nvinfer.dll' in the TensorRT installation directory (typically C:\Program Files\NVIDIA GPU Computing Toolkit\TensorRT\).
    Affected if TensorRT package or library files are present on the system
  2. Determine installed TensorRT version
    Run 'pip show tensorrt' if installed via pip, or check the version from the package manager output from step 1. On Windows, open the TensorRT version from the installation directory folder name or check nvinfer.dll properties.
    Affected if Installed version is any release prior to version 11.0 (e.g., 10.x, 9.x, 8.x, etc.)
  3. Verify TensorRT runtime is in use
    Check for running processes that link against TensorRT libraries: run 'ldd <application>' on Linux or use Process Explorer on Windows to view loaded DLLs. Look for 'nvinfer', 'nvinfer_plugin', or 'cublas' libraries associated with TensorRT.
    Affected if Any application or service loads and uses the TensorRT runtime library
  4. Check for model input handling
    Review application logs or configuration to determine if the system accepts and processes external TensorFlow, ONNX, or custom model files. Inspect any API endpoints or services that accept model uploads or deserialization.
    Affected if The system loads or parses untrusted or externally-provided model files using TensorRT's deserialization APIs

The system is affected if TensorRT is installed with a version lower than 11.0 and processes model inputs, as the heap buffer overflow can be triggered during model parsing.

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 11.0 or later
Fixed in 11.0
Interim mitigation

Apply the NVIDIA TensorRT security patch or update to a patched version once available. If immediate patching is not feasible, restrict network access to systems running TensorRT and ensure proper input validation is performed on model inputs.

Recommended fix Moderate confidence

TensorRT 11.0

  1. 1. Identify the current TensorRT version installed by running 'dpkg -l | grep tensorrt' (Debian/Ubuntu) or 'rpm -qa | grep TensorRT' (RHEL/CentOS)
  2. 2. For CUDA-enabled systems, ensure CUDA version compatibility with TensorRT 11.0 (typically CUDA 11.x or 12.x)
  3. 3. Download TensorRT 11.0 or later from the NVIDIA TensorRT download page (developer.nvidia.com/tensorrt)
  4. 4. Remove the existing TensorRT installation: 'sudo apt remove libnvinfer* libnvparsers* libnvonnxparser*' (Debian) or 'sudo yum remove TensorRT*' (RHEL)
  5. 5. Install the new TensorRT package using the appropriate package manager command for your distribution
  6. 6. Verify the installation by checking the version: 'dpkg -l | grep tensorrt' or checking the library files in /usr/local/cuda/
  7. 7. Test inference workloads to ensure functionality is maintained after upgrade
Caveat Review TensorRT 11.0 release notes for API changes and ensure model compatibility; new major versions may introduce breaking changes in API or supported ONNX operators

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

Fix this in Tensorrt 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-2026-24272 — 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-2026-24272 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