CVE-2026-24213
Possible ATT&CK Techniques 2AI
T1203 · Exploitation for Client Execution T1190 · Exploit Public-Facing ApplicationAffected Version Matrix 1
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| NVIDIA | Triton Inference Server | < r26.03 | affected |
Get alerts for future matching vulnerabilitiesLog in to subscribe
I. Basic Information for CVE-2026-24213
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗ Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
N/A
Source: NVD (National Vulnerability Database)
Vulnerability Description
NVIDIA Triton Inference Server contains a vulnerability in the DALI backend where an attacker could cause an out-of-bounds read. A successful exploit of this vulnerability might lead to code execution, data tampering, denial of service, or information disclosure.
Source: NVD (National Vulnerability Database)
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H
Source: NVD (National Vulnerability Database)
Vulnerability Type
跨界内存读
Source: NVD (National Vulnerability Database)
Vulnerability Title
NVIDIA Triton Inference Server 缓冲区错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
NVIDIA Triton Inference Server是美国英伟达（NVIDIA）公司的一款开源软件，有助于标准化模型部署并在生产中提供快速且可扩展的 AI。 NVIDIA Triton Inference Server存在缓冲区错误漏洞，该漏洞源于DALI后端中的越界读取，可能导致代码执行、数据篡改、拒绝服务或信息泄露。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| NVIDIA | Triton Inference Server | 0 ~ r26.03 | - |
II. Public POCs for CVE-2026-24213
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POCPremium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-24213
请登录查看更多情报信息。
Other · 1Advisory · 1
Same Patch Batch · NVIDIA · 2026-05-20 · 16 CVEs total
| CVE-2026-24207 | 9.8 CRITICAL | NVIDIA Triton Inference Server 安全漏洞 |
| CVE-2026-24217 | 8.8 HIGH | NVIDIA BioNeMo Core 安全漏洞 |
| CVE-2026-24188 | 8.2 HIGH | NVIDIA TensorRT 缓冲区错误漏洞 |
| CVE-2026-24218 | 8.1 HIGH | NVIDIA DGX OS 安全漏洞 |
| CVE-2026-24214 | 8.0 HIGH | NVIDIA Triton Inference Server 输入验证错误漏洞 |
| CVE-2026-24216 | 7.8 HIGH | NVIDIA BioNeMo 代码问题漏洞 |
| CVE-2026-24163 | 7.5 HIGH | NVIDIA TRT-LLM 代码问题漏洞 |
| CVE-2025-33255 | 7.5 HIGH | NVIDIA TRT-LLM 代码问题漏洞 |
| CVE-2026-24210 | 7.5 HIGH | NVIDIA Triton Inference Server 输入验证错误漏洞 |
| CVE-2026-24209 | 7.5 HIGH | NVIDIA Triton Inference Server 路径遍历漏洞 |
| CVE-2026-24206 | 7.3 HIGH | NVIDIA Triton Inference Server 安全漏洞 |
| CVE-2026-24142 | 6.3 MEDIUM | NVIDIA TRT-LLM 代码问题漏洞 |
| CVE-2026-24215 | 5.7 MEDIUM | NVIDIA Triton Inference Server 资源管理错误漏洞 |
| CVE-2026-24160 | 5.5 MEDIUM | NVIDIA TRT-LLM 安全漏洞 |
| CVE-2026-24208 | 5.3 MEDIUM | NVIDIA Triton Inference Server 路径遍历漏洞 |
IV. Related Vulnerabilities
Same weakness: CWE-125
- CVE-2026-41071
libheif: Heap buffer over-read in SampleAuxInfoReader via cr - CVE-2026-41069
libheif allows Out-of-bounds vector access leading to invali - CVE-2026-44067
EA header parsing heap over-read - CVE-2026-44066
Heap out-of-bounds reads in Spotlight RPC unmarshalling - CVE-2026-44064
ASP session ID out-of-bounds access
V. Comments for CVE-2026-24213
No comments yet