Deserialization of Untrusted DataWeakness · CWE-502

CVE-2026-24220

MEDIUM · 6.4 CVSS v3.1 Published 2026-07-14
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
66/100
Remediation priority · Elevated
Zero-click 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-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an unsafe deserialization by unauthorized zeroMQ deserialization. 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-LLM contains an unsafe deserialization vulnerability in its visual gen server component where unauthorized ZeroMQ deserialization can be exploited, potentially allowing remote code execution.

MitigationApply NVIDIA's patch when available; until then, restrict network access to the visual gen server and disable or firewall ZeroMQ ports if possible.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

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

CVSS:3.1/AV:L/AC:H/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. Check if TensorRT-LLM is installed
    Run 'pip show tensorrt-llm' or 'nvidia-smi' and look for TensorRT-LLM package. Check installation directory typically at /usr/local/tensorrt-llm or via pip.
    Affected if TensorRT-LLM is installed and the visual gen server component is in use
  2. Identify the visual gen server component
    Look for process or service named 'visual_gen_server', 'visual-gen', or similar in running processes. Check /opt/nvidia/tensorrt-llm/visual_gen/ or installation paths for visual generation server files.
    Affected if Visual gen server component is running or installed
  3. Verify ZeroMQ is in use
    Check for open ports associated with ZeroMQ (typically ports 5555, 5556, 5570 or configurable). Run 'netstat -tlnp | grep -E "(5555|5556|5570)"' or check process list for zmq-related libraries.
    Affected if ZeroMQ ports are open or ZeroMQ libraries are loaded by the visual gen server
  4. Check ZeroMQ configuration
    Inspect config files in the visual gen server directory for ZeroMQ bind addresses. Look for 'zmq', 'zeromq', 'bind' settings in config.yaml, config.json, or similar files.
    Affected if ZeroMQ is configured to accept remote connections (0.0.0.0 rather than 127.0.0.1)
  5. Review network exposure
    Check firewall rules and network binding configuration. Verify if the visual gen server ZeroMQ ports are exposed to untrusted networks.
    Affected if ZeroMQ ports are accessible from untrusted network segments or internet-facing interfaces

You are affected if TensorRT-LLM with the visual gen server is installed, running, and has ZeroMQ ports exposed to untrusted access, allowing remote attackers to send malicious serialized payloads.

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.

From vendor data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Apply NVIDIA's patch when available; until then, restrict network access to the visual gen server and disable or firewall ZeroMQ ports if possible.

Have this fixed Scoped from the published advisory
  • Consultation3.0 h
  • Implementation6.0 h
  • Testing4.0 h
  • Review / QA2.0 h
15.0 hours of engineering $2,640
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,224.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-24220 — 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-2026-24220 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