SEPTEMBER 11, 2026
Live Feed
Back to database
Case File

CVE-2026-47475

MEDIUM · CVSS 6.2 EPSS 0.12% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-14 · Last synced 2026-08-13

CyberRota Analysis

AI-Generated

NVIDIA TensorRT-LLM is vulnerable in its OpenAI-compatible inference API, where an attacker can exploit a reachable assertion in the sampler thread. This could result in a denial of service, impacting the availability of applications relying on this API. Organizations utilizing TensorRT-LLM for AI inference should prioritize addressing this vulnerability to maintain system stability and performance.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Detected Signals
exploit

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-47475
Severity
MEDIUM
CVSS
6.2
EPSS
0.12%

Original NVD Description

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.