What is the CVSS score of EUVD-2026-31057?

EUVD-2026-31057 has a CVSS 3.1 base score of 7.5 (High). CVSS vector: CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H. EPSS exploitation probability: 0.1%.

Which versions of NVIDIA TensorRT-LLM are affected by EUVD-2026-31057?

NVIDIA TensorRT-LLM's RPC testing component contains an unsafe deserialization flaw enabling local high-privilege attackers to execute code, disrupt service, or tamper with AI model data.

How to fix or mitigate EUVD-2026-31057?

Within 24 hours: Inventory all NVIDIA TensorRT-LLM deployments and document RPC component usage. Within 7 days: Disable RPC testing component if operationally unnecessary; implement OS-level privilege restrictions limiting access to essential personnel only. Within 30 days: Establish network segmentation isolating TensorRT-LLM systems; configure audit logging for deserialization operations; monitor NVIDIA advisories for patch availability and schedule upgrade planning.

NVIDIA TensorRT-LLM EUVD-2026-31057

| CVE-2026-24163 HIGH

Deserialization of Untrusted Data (CWE-502)

2026-05-20 nvidia

GHSA-qvvq-q6v7-7fhg

Information Disclosure Deserialization RCE Denial Of Service Nvidia

7.5

CVSS 3.1 · NVD

Severity by source

NVD PRIMARY

7.5 HIGH

AV:L/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H

Attack Vector

Local

Attack Complexity

High

Privileges Required

High

User Interaction

None

Scope

Changed

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

May 20, 2026 - 04:01 vuln.today

DescriptionCVE.org

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.

AnalysisAI

Unsafe deserialization in NVIDIA TensorRT-LLM's RPC testing component allows a local high-privileged attacker to trigger code execution, denial of service, data tampering, or information disclosure across a changed scope. The flaw is rated CVSS 7.5 despite local-only access and high attack complexity because successful exploitation crosses a security boundary (S:C) and yields full CIA impact. No public exploit identified at time of analysis, and the issue is not listed in CISA KEV.

Technical ContextAI

TensorRT-LLM (TRT-LLM) is NVIDIA's open-source library for optimizing and serving large language model inference on NVIDIA GPUs, commonly deployed in AI inference clusters and used with Triton Inference Server. The vulnerability resides in an RPC-based testing pathway and is classified as CWE-502 (Deserialization of Untrusted Data), meaning the component reconstructs language-native objects (likely Python pickle, given the TRT-LLM Python stack) from attacker-influenced byte streams without validating the type or contents. When deserialization is performed on untrusted input, gadget chains in the loaded modules can be invoked during object reconstruction, turning a data parse into arbitrary execution. The single affected CPE entry (cpe:2.3:a:nvidia:tensorrt-llm:*:*:*:*:*:*:*:*) covers all versions of the product up to the vendor-released fix.

RemediationAI

Patch available per vendor advisory - upgrade NVIDIA TensorRT-LLM to the fixed release identified in NVIDIA bulletin 5805 (https://nvidia.custhelp.com/app/answers/detail/a_id/5805); exact fixed version is not enumerated in the supplied data and should be taken from that advisory. Until the upgrade is deployed, do not expose the TRT-LLM RPC testing interface beyond trusted operators, remove or disable test/RPC entry points in production inference deployments, and restrict file-system and process access on inference hosts so that only the dedicated service account can reach the RPC socket (trade-off: this may break developer test workflows that rely on the same RPC path). For multi-tenant inference clusters, segment tenants onto separate hosts or namespaces to prevent a compromised tenant from reaching another tenant's TRT-LLM process via the changed-scope component.