# Nvidia TensorRT-LLM vulnerabilities

Source: https://junglewise.ai/threats/technologies/tensorrt-llm  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Updated: 9 November 2026, 03:07 UTC. Rebuilt every hour.  
Data: https://junglewise.ai/threats/technologies/tensorrt-llm.json  
License: CC BY 4.0 with a link back

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.

## Counts

- Last 7 days: 0
- Last 30 days: 3
- Last 90 days: 3
- All time: 16 (0 critical, 0 exploited in the wild)

## 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 forgery](https://junglewise.ai/threats/cve-2026-65120-nvidia-tensorrt-llm-contains-a-vulnerability-where-an-attacker) (high, CVSS 7.1, published 27 Oct 2026)
- [CVE-2026-65119: NVIDIA TensorRT-LLM untrusted tokenizer loading in KvCacheAwareRouter](https://junglewise.ai/threats/cve-2026-65119-nvidia-tensorrt-llm-for-any-platform-contains-a-vulnerability-in) (high, CVSS 8.4, published 27 Oct 2026)
- [CVE-2026-24269: NVIDIA TensorRT-LLM server-side request forgery](https://junglewise.ai/threats/cve-2026-24269-nvidia-tensorrt-llm-contains-a-vulnerability-where-an-attacker) (high, CVSS 7.1, published 27 Oct 2026)
- [CVE-2026-47475: NVIDIA TensorRT-LLM denial of service in OpenAI-compatible API](https://junglewise.ai/threats/cve-2026-47475-nvidia-tensorrt-llm-denial-of-service-in-openai-compatible-api) (medium, CVSS 6.2, published 14 Jul 2026)
- [CVE-2026-47473: NVIDIA TensorRT-LLM write-what-where condition](https://junglewise.ai/threats/cve-2026-47473-nvidia-tensorrt-llm-write-what-where-condition) (high, CVSS 7.4, published 14 Jul 2026)
- [CVE-2026-47472: NVIDIA TensorRT-LLM deserialization in IPC layer](https://junglewise.ai/threats/cve-2026-47472-nvidia-tensorrt-llm-deserialization-in-ipc-layer) (high, CVSS 7.8, published 14 Jul 2026)
- [CVE-2026-47471: NVIDIA TensorRT-LLM heap buffer overflow in tensor deserialization](https://junglewise.ai/threats/cve-2026-47471-nvidia-tensorrt-llm-heap-buffer-overflow-in-tensor) (high, CVSS 7.5, published 14 Jul 2026)
- [CVE-2026-47470: NVIDIA TensorRT-LLM improper input validation in gRPC server chat API](https://junglewise.ai/threats/cve-2026-47470-nvidia-tensorrt-llm-improper-input-validation-in-grpc-server-chat) (medium, CVSS 6.2, published 14 Jul 2026)
- [CVE-2026-24271: NVIDIA TensorRT-LLM resource exhaustion in OpenAI-compatible API](https://junglewise.ai/threats/cve-2026-24271-nvidia-tensorrt-llm-resource-exhaustion-in-openai-compatible-api) (medium, CVSS 6.2, published 14 Jul 2026)
- [CVE-2026-24259: NVIDIA TensorRT-LLM missing authentication in critical function](https://junglewise.ai/threats/cve-2026-24259-nvidia-tensorrt-llm-missing-authentication-in-critical-function) (medium, CVSS 6.4, published 14 Jul 2026)
- [CVE-2026-24234: NVIDIA TensorRT-LLM SSRF in multimodal media fetching functions](https://junglewise.ai/threats/cve-2026-24234-nvidia-tensorrt-llm-ssrf-in-multimodal-media-fetching-functions) (medium, CVSS 6.8, published 14 Jul 2026)
- [CVE-2026-24233: NVIDIA TensorRT-LLM deserialization in model weight unpickler](https://junglewise.ai/threats/cve-2026-24233-nvidia-tensorrt-llm-deserialization-in-model-weight-unpickler) (high, CVSS 8.4, published 14 Jul 2026)
- [CVE-2026-24229: NVIDIA TensorRT-LLM missing authentication in disaggregated orchestrator](https://junglewise.ai/threats/cve-2026-24229-nvidia-tensorrt-llm-missing-authentication-in-disaggregated) (high, CVSS 7.3, published 14 Jul 2026)
- [CVE-2026-24226: NVIDIA TensorRT-LLM improper control of code generation](https://junglewise.ai/threats/cve-2026-24226-nvidia-tensorrt-llm-improper-control-of-code-generation) (medium, CVSS 6.3, published 14 Jul 2026)
- [CVE-2026-24220: NVIDIA TensorRT-LLM unsafe deserialization in visual gen server](https://junglewise.ai/threats/cve-2026-24220-nvidia-tensorrt-llm-unsafe-deserialization-in-visual-gen-server) (medium, CVSS 6.4, published 14 Jul 2026)
- [CVE-2026-24142: NVIDIA TRT-LLM deserialization vulnerability](https://junglewise.ai/threats/cve-2026-24142-nvidia-trt-llm-deserialization-vulnerability) (medium, CVSS 6.3, published 20 May 2026)

## Most severe Nvidia TensorRT-LLM vulnerabilities

- [CVE-2026-65119: NVIDIA TensorRT-LLM untrusted tokenizer loading in KvCacheAwareRouter](https://junglewise.ai/threats/cve-2026-65119-nvidia-tensorrt-llm-for-any-platform-contains-a-vulnerability-in) (high, CVSS 8.4, published 27 Oct 2026)
- [CVE-2026-24233: NVIDIA TensorRT-LLM deserialization in model weight unpickler](https://junglewise.ai/threats/cve-2026-24233-nvidia-tensorrt-llm-deserialization-in-model-weight-unpickler) (high, CVSS 8.4, published 14 Jul 2026)
- [CVE-2026-47472: NVIDIA TensorRT-LLM deserialization in IPC layer](https://junglewise.ai/threats/cve-2026-47472-nvidia-tensorrt-llm-deserialization-in-ipc-layer) (high, CVSS 7.8, published 14 Jul 2026)
- [CVE-2026-47471: NVIDIA TensorRT-LLM heap buffer overflow in tensor deserialization](https://junglewise.ai/threats/cve-2026-47471-nvidia-tensorrt-llm-heap-buffer-overflow-in-tensor) (high, CVSS 7.5, published 14 Jul 2026)
- [CVE-2026-47473: NVIDIA TensorRT-LLM write-what-where condition](https://junglewise.ai/threats/cve-2026-47473-nvidia-tensorrt-llm-write-what-where-condition) (high, CVSS 7.4, published 14 Jul 2026)
- [CVE-2026-24229: NVIDIA TensorRT-LLM missing authentication in disaggregated orchestrator](https://junglewise.ai/threats/cve-2026-24229-nvidia-tensorrt-llm-missing-authentication-in-disaggregated) (high, CVSS 7.3, published 14 Jul 2026)
- [CVE-2026-65120: NVIDIA TensorRT-LLM server-side request forgery](https://junglewise.ai/threats/cve-2026-65120-nvidia-tensorrt-llm-contains-a-vulnerability-where-an-attacker) (high, CVSS 7.1, published 27 Oct 2026)
- [CVE-2026-24269: NVIDIA TensorRT-LLM server-side request forgery](https://junglewise.ai/threats/cve-2026-24269-nvidia-tensorrt-llm-contains-a-vulnerability-where-an-attacker) (high, CVSS 7.1, published 27 Oct 2026)
- [CVE-2026-24234: NVIDIA TensorRT-LLM SSRF in multimodal media fetching functions](https://junglewise.ai/threats/cve-2026-24234-nvidia-tensorrt-llm-ssrf-in-multimodal-media-fetching-functions) (medium, CVSS 6.8, published 14 Jul 2026)
- [CVE-2026-24259: NVIDIA TensorRT-LLM missing authentication in critical function](https://junglewise.ai/threats/cve-2026-24259-nvidia-tensorrt-llm-missing-authentication-in-critical-function) (medium, CVSS 6.4, published 14 Jul 2026)

## Vulnerabilities per week

3 vulnerabilities in the last four weeks, up from none in the four before.

| Week of | Vulns | Critical | Exploited |
| --- | --- | --- | --- |
| 17 Aug 2026 | 0 | 0 | 0 |
| 24 Aug 2026 | 0 | 0 | 0 |
| 31 Aug 2026 | 0 | 0 | 0 |
| 7 Sep 2026 | 0 | 0 | 0 |
| 14 Sep 2026 | 0 | 0 | 0 |
| 21 Sep 2026 | 0 | 0 | 0 |
| 28 Sep 2026 | 0 | 0 | 0 |
| 5 Oct 2026 | 0 | 0 | 0 |
| 12 Oct 2026 | 0 | 0 | 0 |
| 19 Oct 2026 | 0 | 0 | 0 |
| 26 Oct 2026 | 3 | 0 | 0 |
| 2 Nov 2026 | 0 | 0 | 0 |
| 9 Nov 2026 | 0 | 0 | 0 |

## Other Nvidia technologies

- [NVIDIA GPU Display Driver](https://junglewise.ai/threats/technologies/gpu-display-driver): 74 vulnerabilities
- [Nvidia Megatron-Bridge](https://junglewise.ai/threats/technologies/megatron-bridge): 43 vulnerabilities
- [Nvidia Triton Inference Server](https://junglewise.ai/threats/technologies/triton-inference-server): 33 vulnerabilities
- [Nvidia NeMo Megatron Bridge](https://junglewise.ai/threats/technologies/nemo-megatron-bridge): 32 vulnerabilities
- [Nvidia GPU Display Driver for Linux](https://junglewise.ai/threats/technologies/gpu-display-driver-for-linux): 22 vulnerabilities
- [Nvidia Dynamo](https://junglewise.ai/threats/technologies/dynamo): 15 vulnerabilities
- [Nvidia GPU Display Driver for Windows](https://junglewise.ai/threats/technologies/gpu-display-driver-for-windows): 14 vulnerabilities
- [Nvidia Infrastructure Controller for Linux](https://junglewise.ai/threats/technologies/infrastructure-controller-for-linux): 14 vulnerabilities
- [Nvidia Nemoclaw](https://junglewise.ai/threats/technologies/nemoclaw): 14 vulnerabilities
- [Nvidia vGPU Virtual GPU Manager](https://junglewise.ai/threats/technologies/vgpu-virtual-gpu-manager): 10 vulnerabilities
- [Nvidia AIStore](https://junglewise.ai/threats/technologies/aistore): 9 vulnerabilities
- [Nvidia DALI](https://junglewise.ai/threats/technologies/dali): 7 vulnerabilities

## Sources

NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "Nvidia TensorRT-LLM vulnerabilities", https://junglewise.ai/threats/technologies/tensorrt-llm, 9 November 2026.
