Tensorrt LLM
by Nvidia
Source repositories
CVEs (17)
| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2025-23254 | Hig | 0.57 | 8.8 | 0.00 | May 1, 2025 | NVIDIA TensorRT-LLM for any platform contains a vulnerability in python executor where an attacker may cause a data validation issue by local access to the TRTLLM server. A successful exploit of this vulnerability may lead to code execution, information disclosure and data… | ||
| CVE-2026-24163 | Hig | 0.49 | 7.5 | 0.01 | May 20, 2026 | NVIDIA TRT-LLM for any platform contains a vulnerability in RPC testing, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure. | ||
| CVE-2025-33255 | Hig | 0.49 | 7.5 | 0.01 | May 20, 2026 | NVIDIA TRT-LLM for any platform contains a vulnerability in MPI server, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure. | ||
| CVE-2026-24142 | Med | 0.41 | 6.3 | 0.00 | May 20, 2026 | NVIDIA TRT-LLM for any platform contains a deserialization vulnerability and unsafe serialized handle. A successful exploit of this vulnerability might lead to code execution, data tampering, and information disclosure. | ||
| CVE-2026-24160 | Med | 0.36 | 5.5 | 0.00 | May 20, 2026 | NVIDIA TRT-LLM for any platform contains a vulnerability where an attacker could cause an unchecked return value to a null pointer dereference. A successful exploit of this vulnerability might lead to denial of service. | ||
| CVE-2026-47475 | Med | 0.00 | 6.2 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service. | ||
| CVE-2026-47473 | Hig | 0.00 | 7.4 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM contains a vulnerability where an attacker could cause a write-what-where condition. A successful exploit of this vulnerability might lead to data tampering, denial of service, and information disclosure. | ||
| CVE-2026-47472 | Hig | 0.00 | 7.8 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM contains a vulnerability in its inter-process communication layer where an attacker with local same-user access could cause deserialization. A successful exploit of this vulnerability might lead to code execution, information disclosure, data tampering, and… | ||
| CVE-2026-47471 | Hig | 0.00 | 7.5 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service. | ||
| CVE-2026-47470 | Med | 0.00 | 6.2 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM for any platform contains a vulnerability in the gRPC server chat API endpoint, where an attacker could cause CWE-20 by local attack. A successful exploit of this vulnerability might lead to denial of service. | ||
| CVE-2026-24271 | Med | 0.00 | 6.2 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits or throttling. A successful exploit of this vulnerability might lead to denial of service. | ||
| CVE-2026-24259 | Med | 0.00 | 6.4 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM for Linux contains a vulnerability where an attacker could cause missing authentication for a critical function. A successful exploit of this vulnerability might lead to code execution, data tampering, and information disclosure. | ||
| CVE-2026-24234 | Med | 0.00 | 6.8 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM for Linux contains a vulnerability in the multimodal media fetching functions, where a network-accessible attacker could cause server-side request forgery. A successful exploit of this vulnerability might lead to denial of service and information disclosure. | ||
| CVE-2026-24233 | Hig | 0.00 | 8.4 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code… | ||
| CVE-2026-24229 | Hig | 0.00 | 7.3 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM for Linux contains a vulnerability in the disaggregated orchestrator component, where an attacker could read, write, or delete internal cluster state by sending requests to the FastAPI server. A successful exploit of this vulnerability might lead to… | ||
| CVE-2026-24226 | Med | 0.00 | 6.3 | 0.00 | Jul 14, 2026 | NVIDIA TensorRT-LLM for Linux contains a vulnerability where an attacker could cause improper control of code generation. A successful exploit of this vulnerability might lead to code execution, data tampering, and information disclosure. | ||
| CVE-2026-24220 | Med | 0.00 | 6.4 | 0.00 | Jul 14, 2026 | 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. |
- risk 0.57cvss 8.8epss 0.00
NVIDIA TensorRT-LLM for any platform contains a vulnerability in python executor where an attacker may cause a data validation issue by local access to the TRTLLM server. A successful exploit of this vulnerability may lead to code execution, information disclosure and data…
- risk 0.49cvss 7.5epss 0.01
NVIDIA TRT-LLM for any platform contains a vulnerability in RPC testing, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure.
- risk 0.49cvss 7.5epss 0.01
NVIDIA TRT-LLM for any platform contains a vulnerability in MPI server, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure.
- risk 0.41cvss 6.3epss 0.00
NVIDIA TRT-LLM for any platform contains a deserialization vulnerability and unsafe serialized handle. A successful exploit of this vulnerability might lead to code execution, data tampering, and information disclosure.
- risk 0.36cvss 5.5epss 0.00
NVIDIA TRT-LLM for any platform contains a vulnerability where an attacker could cause an unchecked return value to a null pointer dereference. A successful exploit of this vulnerability might lead to denial of service.
- risk 0.00cvss 6.2epss 0.00
NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.
- risk 0.00cvss 7.4epss 0.00
NVIDIA TensorRT-LLM contains a vulnerability where an attacker could cause a write-what-where condition. A successful exploit of this vulnerability might lead to data tampering, denial of service, and information disclosure.
- risk 0.00cvss 7.8epss 0.00
NVIDIA TensorRT-LLM contains a vulnerability in its inter-process communication layer where an attacker with local same-user access could cause deserialization. A successful exploit of this vulnerability might lead to code execution, information disclosure, data tampering, and…
- risk 0.00cvss 7.5epss 0.00
NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service.
- risk 0.00cvss 6.2epss 0.00
NVIDIA TensorRT-LLM for any platform contains a vulnerability in the gRPC server chat API endpoint, where an attacker could cause CWE-20 by local attack. A successful exploit of this vulnerability might lead to denial of service.
- risk 0.00cvss 6.2epss 0.00
NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits or throttling. A successful exploit of this vulnerability might lead to denial of service.
- risk 0.00cvss 6.4epss 0.00
NVIDIA TensorRT-LLM for Linux contains a vulnerability where an attacker could cause missing authentication for a critical function. A successful exploit of this vulnerability might lead to code execution, data tampering, and information disclosure.
- risk 0.00cvss 6.8epss 0.00
NVIDIA TensorRT-LLM for Linux contains a vulnerability in the multimodal media fetching functions, where a network-accessible attacker could cause server-side request forgery. A successful exploit of this vulnerability might lead to denial of service and information disclosure.
- risk 0.00cvss 8.4epss 0.00
NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code…
- risk 0.00cvss 7.3epss 0.00
NVIDIA TensorRT-LLM for Linux contains a vulnerability in the disaggregated orchestrator component, where an attacker could read, write, or delete internal cluster state by sending requests to the FastAPI server. A successful exploit of this vulnerability might lead to…
- risk 0.00cvss 6.3epss 0.00
NVIDIA TensorRT-LLM for Linux contains a vulnerability where an attacker could cause improper control of code generation. A successful exploit of this vulnerability might lead to code execution, data tampering, and information disclosure.
- risk 0.00cvss 6.4epss 0.00
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.