dbcve.org
Tensorrt LlmApplication · Nvidia

CVE-2025-33255

CRITICAL · 9.8 CVSS v3.1 Published 2026-05-20
Fix available
A fix is available. Upgrade to 1.2 or later.
See remediation →
100/100
Remediation priority · Urgent
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 TRT-LLM for any platform contains a vulnerability in MPI server, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure.

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 · high confidence

NVIDIA TRT-LLM contains an unsafe deserialization vulnerability in its MPI server component. This allows an attacker to potentially exploit deserialization of untrusted data, leading to arbitrary code execution, denial of service, data tampering, or information disclosure.

MitigationApply available patches or updates from NVIDIA for TRT-LLM that address the unsafe deserialization in the MPI server. If no patch is available, restrict network access to the MPI server and implement input validation on serialized data.

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
Tensorrt LlmApplication
Affected:< 1.2

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
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/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. Confirm NVIDIA TensorRT-LLM installation
    Locate the TensorRT-LLM installation directory or check installed packages using package manager or NVIDIA's tooling (e.g., 'pip show tensorrt-llm' or check /usr/local/tensorrt_llm)
    Affected if TensorRT-LLM is not installed or cannot be found
  2. Determine installed TensorRT-LLM version
    Run 'tensorrt_llm.__version__' in Python, or use 'pip show tensorrt-llm', or check the version file in the installation directory
    Affected if The installed version is less than 1.2.0 (e.g., 1.0.x, 1.1.x)
  3. Check if MPI server component is in use
    Inspect running processes for mpirun, mpiexec, or trt-llm-mpi-server. Review any configuration files that enable or reference MPI distributed inference. Check for MPI-related environment variables (e.g., MPI-related ports, worker configurations)
    Affected if MPI server is enabled or configured for distributed inference workloads
  4. Inspect network exposure of MPI services
    Review network configuration and firewall rules for ports used by MPI (commonly derived from PMIx/PMI interface). Check if MPI server ports are accessible from untrusted network segments
    Affected if MPI server ports are exposed to untrusted or external networks

A user is affected if TensorRT-LLM version is below 1.2 AND the MPI server component is enabled or in use within their environment.

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 1.2 or later
Fixed in 1.2
Interim mitigation

Apply available patches or updates from NVIDIA for TRT-LLM that address the unsafe deserialization in the MPI server. If no patch is available, restrict network access to the MPI server and implement input validation on serialized data.

Recommended fix Moderate confidence

TensorRT LLM version 1.2 or later

  1. 1. Identify current TensorRT LLM version using `pip show tensorrt-llm` or checking the container image tag
  2. 2. Backup any custom models, configurations, and scripts before upgrading
  3. 3. Upgrade TensorRT LLM to version 1.2 or later using the appropriate installation method (pip, container, or build from source)
  4. 4. Verify the upgrade was successful by checking the installed version
  5. 5. Test critical inference workloads to ensure functionality is preserved
  6. 6. Review MPI server configuration to ensure no custom configurations bypass security settings
Caveat Review release notes for any API changes or deprecated features between your current version and 1.2 that may require code modifications

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

Fix this in Tensorrt Llm Scoped from the published advisory
  • Consultation6.0 h
  • Implementation12.0 h
  • Testing10.0 h
  • Review / QA5.0 h
33.0 hours of engineering $5,760
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $9,216.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-33255 — 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-2025-33255 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