Skip to main content
CVE-2026-24220VulnerabilityPublished Updated

NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an

Affects tensorrt-llmSource GCVE Database

0
Compare
Authoritative record:CVE-2026-24220· Medium 6.4

Not known to be exploited · CVSS 6.4 Medium : upgrade to 1.4.0rc0 when convenient.

Data as of 20 Nov 2026, 05:04 UTC

CVSS 3.1 base score
6.4Medium
How severe the flaw is on the 0–10 CVSS scale.
Patch
Available – fixed in 1.4.0rc0
CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:H

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 14 Jul 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 19 Nov 2026.

What to do

Upgrade tensorrt-llm to 1.4.0rc0.

Affected software

ProductAffectedFixed in
PyPItensorrt-llmpkg:pypi/tensorrt-llmOther threatsAffected
  • <1.4.0rc0
Fixed in
  • 1.4.0rc0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

A patch is available in NVIDIA TensorRT-LLM version 1.4.0rc0. Users should upgrade to this version or later to remediate the vulnerability. Since the vulnerability requires local access with high privileges, limiting such access can reduce risk until patched.

Description

NVIDIA TensorRT-LLM contains a vulnerability in its visual gen server component that allows unauthorized zeroMQ deserialization, potentially leading to unsafe deserialization. Exploiting this flaw could enable an attacker with local access and high privileges to execute arbitrary code. The vulnerability affects multiple versions prior to 1.4.0rc0 and has a medium severity rating with a CVSS score of 6.4. A patch is available in version 1.4.0rc0.

References

Community reviews

Loading reviews…