Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%

CVE-2026-24233

Quick assessment

Affected
NVIDIA TensorRT-LLM
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

NVIDIA TensorRT-LLM是美国NVIDIA公司的深度学习优化库。 NVIDIA TensorRT-LLM v1.3.0 rc14及之前版本存在反序列化注入漏洞,该漏洞源于用于模型权重反序列化的受限解包器存在反序列化不可信数据问题,可能导致代码执行、权限提升、数据篡改和信息泄露。

CVSS 8.4 · High EPSS 0.39% · P31

Possible ATT&CK Techniques 1 AI

T1203 · Exploitation for Client Execution

Affected Version Matrix 1

VendorProduct Version RangeStatus
NVIDIA TensorRT-LLM 0.0≤ v1.3.0 rc14 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-24233

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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: CVE Program / CVE List V5
Vulnerability Description
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 execution, escalation of privileges, data tampering, and information disclosure.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
可信数据的反序列化
Source: CVE Program / CVE List V5
Vulnerability Title
NVIDIA TensorRT-LLM 反序列化注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
NVIDIA TensorRT-LLM是美国NVIDIA公司的深度学习优化库。 NVIDIA TensorRT-LLM v1.3.0 rc14及之前版本存在反序列化注入漏洞,该漏洞源于用于模型权重反序列化的受限解包器存在反序列化不可信数据问题,可能导致代码执行、权限提升、数据篡改和信息泄露。
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 TensorRT-LLM 0.0 ~ v1.3.0 rc14 -

II. Public POCs for CVE-2026-24233

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-24233

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-24233 (1)

Other References for CVE-2026-24233 (1)

Same Patch Batch · NVIDIA · 2026-07-14 · 23 CVEs total

CVE-2026-47472 7.8 HIGH NVIDIA TensorRT-LLM 反序列化注入漏洞
CVE-2026-24268 7.8 HIGH NVIDIA TensorRT 缓冲区错误漏洞
CVE-2026-24272 7.8 HIGH NVIDIA TensorRT 缓冲区错误漏洞
CVE-2026-24238 7.8 HIGH NVIDIA TensorRT 输入验证错误漏洞
CVE-2026-47482 7.5 HIGH NVIDIA Triton Inference Server 资源管理错误漏洞
CVE-2026-47471 7.5 HIGH NVIDIA TensorRT-LLM 缓冲区错误漏洞
CVE-2026-47477 7.5 HIGH NVIDIA Triton Inference Server 缓冲区错误漏洞
CVE-2026-47476 7.5 HIGH NVIDIA Triton Inference Server 资源管理错误漏洞
CVE-2026-47479 7.5 HIGH NVIDIA Triton Inference Server 资源管理错误漏洞
CVE-2026-47480 7.5 HIGH NVIDIA Triton Inference Server 异常处理不当漏洞
CVE-2026-47478 7.5 HIGH NVIDIA Triton Inference Server 资源管理错误漏洞
CVE-2026-47473 7.4 HIGH NVIDIA TensorRT-LLM 缓冲区错误漏洞
CVE-2026-24229 7.3 HIGH NVIDIA TensorRT-LLM 授权问题漏洞
CVE-2026-24234 6.8 MEDIUM NVIDIA TensorRT-LLM 服务端请求伪造漏洞
CVE-2026-47481 6.5 MEDIUM NVIDIA Triton Inference Server 授权问题漏洞
CVE-2026-24220 6.4 MEDIUM NVIDIA TensorRT-LLM 反序列化注入漏洞
CVE-2026-24259 6.4 MEDIUM NVIDIA TensorRT-LLM 授权问题漏洞
CVE-2026-24226 6.3 MEDIUM NVIDIA TensorRT-LLM 软件供应链问题漏洞
CVE-2026-24271 6.2 MEDIUM NVIDIA TensorRT-LLM 资源管理错误漏洞
CVE-2026-47475 6.2 MEDIUM NVIDIA TensorRT-LLM 异常处理不当漏洞

Showing top 20 of 23 CVEs. View all on vendor page → →

IV. Related Vulnerabilities

V. Comments for CVE-2026-24233

No comments yet


Leave a comment