NVIDIA TensorRT-LLM for any platform contains a vulnerability in visual gen server, where an attacker could cause an
Affects tensorrt-llmSource GCVE Database
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
- 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:HExploitation evidence
Disclosed: evidence found.
CVE published 14 Jul 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by 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
| Product | Affected | Fixed in |
|---|---|---|
PyPItensorrt-llmpkg:pypi/tensorrt-llmOther threats | Affected
| Fixed in
|
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.