Technology · Nvidia
Nvidia TensorRT-LLM vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 16 vulnerabilities in Nvidia TensorRT-LLM: 0 in the last 7 days and 3 in the last 90 days, 0 of them critical and 0 exploited in the wild. The most recent, CVE-2026-65120, was published on 27 October 2026. 3 vulnerabilities in the last four weeks, up from none in the four before.
- Last 7 days
- 0
- Last 90 days
- 3
- Critical, all time
- 0
- Exploited in the wild
- 0
About Nvidia TensorRT-LLM
An open-source library for optimizing and accelerating large language model (LLM) inference on NVIDIA GPUs.
Latest Nvidia TensorRT-LLM vulnerabilities
- CVE-2026-65120: NVIDIA TensorRT-LLM server-side request forgeryhighCVSS 7.1
- CVE-2026-65119: NVIDIA TensorRT-LLM untrusted tokenizer loading in KvCacheAwareRouterhighCVSS 8.4
- CVE-2026-24269: NVIDIA TensorRT-LLM server-side request forgeryhighCVSS 7.1
- CVE-2026-47475: NVIDIA TensorRT-LLM denial of service in OpenAI-compatible APImediumCVSS 6.2
- CVE-2026-47473: NVIDIA TensorRT-LLM write-what-where conditionhighCVSS 7.4
- CVE-2026-47472: NVIDIA TensorRT-LLM deserialization in IPC layerhighCVSS 7.8
- CVE-2026-47471: NVIDIA TensorRT-LLM heap buffer overflow in tensor deserializationhighCVSS 7.5
- CVE-2026-47470: NVIDIA TensorRT-LLM improper input validation in gRPC server chat APImediumCVSS 6.2
- CVE-2026-24271: NVIDIA TensorRT-LLM resource exhaustion in OpenAI-compatible APImediumCVSS 6.2
- CVE-2026-24259: NVIDIA TensorRT-LLM missing authentication in critical functionmediumCVSS 6.4
- CVE-2026-24234: NVIDIA TensorRT-LLM SSRF in multimodal media fetching functionsmediumCVSS 6.8
- CVE-2026-24233: NVIDIA TensorRT-LLM deserialization in model weight unpicklerhighCVSS 8.4
- CVE-2026-24229: NVIDIA TensorRT-LLM missing authentication in disaggregated orchestratorhighCVSS 7.3
- CVE-2026-24226: NVIDIA TensorRT-LLM improper control of code generationmediumCVSS 6.3
- CVE-2026-24220: NVIDIA TensorRT-LLM unsafe deserialization in visual gen servermediumCVSS 6.4
- CVE-2026-24142: NVIDIA TRT-LLM deserialization vulnerabilitymediumCVSS 6.3
Most severe Nvidia TensorRT-LLM vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-65119: NVIDIA TensorRT-LLM untrusted tokenizer loading in KvCacheAwareRouterhighCVSS 8.4
- CVE-2026-24233: NVIDIA TensorRT-LLM deserialization in model weight unpicklerhighCVSS 8.4
- CVE-2026-47472: NVIDIA TensorRT-LLM deserialization in IPC layerhighCVSS 7.8
- CVE-2026-47471: NVIDIA TensorRT-LLM heap buffer overflow in tensor deserializationhighCVSS 7.5
- CVE-2026-47473: NVIDIA TensorRT-LLM write-what-where conditionhighCVSS 7.4
- CVE-2026-24229: NVIDIA TensorRT-LLM missing authentication in disaggregated orchestratorhighCVSS 7.3
- CVE-2026-65120: NVIDIA TensorRT-LLM server-side request forgeryhighCVSS 7.1
- CVE-2026-24269: NVIDIA TensorRT-LLM server-side request forgeryhighCVSS 7.1
- CVE-2026-24234: NVIDIA TensorRT-LLM SSRF in multimodal media fetching functionsmediumCVSS 6.8
- CVE-2026-24259: NVIDIA TensorRT-LLM missing authentication in critical functionmediumCVSS 6.4
Vulnerabilities per week
3 vulnerabilities in the last four weeks, up from none in the four before. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 | |
| 28 Sep 2026 | 0 | 0 | |
| 5 Oct 2026 | 0 | 0 | |
| 12 Oct 2026 | 0 | 0 | |
| 19 Oct 2026 | 0 | 0 | |
| 26 Oct 2026 | 3 | 0 | |
| 2 Nov 2026 | 0 | 0 | |
| 9 Nov 2026 | 0 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many Nvidia TensorRT-LLM vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/technologies/tensorrt-llm)<a href="https://junglewise.ai/threats/technologies/tensorrt-llm"><img src="https://junglewise.ai/threats/technologies/tensorrt-llm/badge.svg" alt="Nvidia TensorRT-LLM vulnerabilities" /></a>How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/technologies/tensorrt-llm.json, and this page as text at https://junglewise.ai/threats/technologies/tensorrt-llm.md, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Nvidia TensorRT-LLM vulnerabilities", https://junglewise.ai/threats/technologies/tensorrt-llm, 9 November 2026.