r2d2

r2d2 用于 radare2 的 GPT-4 插件 简介 这是一个 radare2 插件，利用 GPT-4 让 GPT-4 直接发布 r2 命令并解释输出结果。 https://github.com/dnakov/r2d2/assets/3777433/4bc7b211-bccc-4b04-9350-6bfca8989edb https://github.com/dnakov/r2d2/assets/3777433/5bcc8e20-dda0-48ac-94e5-e0c8c44a0912 安装 从源码安装...

IDA_Plugin_PCodeGPT

PCodeGPT Un plugin para ida 7.5 7.x y 8.x. Descripción Este es un plugin de IDA modificado de gepetto y WPeChatGPT que utilizo para automatizar el análisis de código usando GPT 3.5 o GPT-4 de OpenAI. Actualmente, solo se admite chino. Uso Mueve PCodeGPT.py a la carpeta plugins, y el plugin se...

llm-security

新：演示对 Bing Chat 的间接注入攻击 利用间接提示注入攻陷 LLM “……语言模型是一台图灵完备的怪异机器，运行着用自然语言编写的程序；当你进行检索时，你并不是在‘把更新的事实插入你的 AI’，而是在从互联网下载随机的、未签名的代码块（许多由对手编写），并随意地以完全权限在你的 LM 上执行它们。这不会有好结果。” - Gwern Branwen 在 LessWrong 上 我们提出了一类新的漏洞及其影响，源于影响与应用程序集成的语言模型的“间接提示注入”。 我们目前的演示涵盖使用 ChatML 的 GPT-4（Bing 和合成应用）、基于 GPT-3 和 LangChain...

EUVD-2023-41186

Malicious code in bioql PyPI...

EUVD-2025-21932

Malicious code in bioql PyPI...

EUVD-2023-56239

Malicious code in bioql PyPI...

EUVD-2023-49384

Malicious code in bioql PyPI...

EUVD-2024-45879

Malicious code in bioql PyPI...

EUVD-2023-56240

Malicious code in bioql PyPI...

CVE-2025-50709

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

CVE-2025-50709

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

CVE-2025-50709: Use of GET Request Method With Sensitive Query Strings

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

CVE-2025-50708

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

CVE-2025-50708

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

PT-2025-30092 · Unknown · Perplexity Ai Gpt-4

Name of the Vulnerable Software and Affected Versions: Perplexity AI GPT-4 version 2.51.0 Description: An issue allows a remote attacker to obtain sensitive information via the token component in the shared chat URL. Recommendations: At the moment, there is no information about a newer version th...

CVE-2025-50708

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

CVE-2025-50708: Exposure of Sensitive Information to an Unauthorized Actor

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

CVE-2025-6206: Unrestricted Upload of File with Dangerous Type

The Aiomatic - Automatic AI Content Writer & Editor, GPT-3 & GPT-4, ChatGPT ChatBot & AI Toolkit plugin for WordPress is vulnerable to arbitrary file uploads due to missing file type validation in the 'aiomaticimageeditorajaxsubmit' function in all versions up to, and including, 2.5.0. This makes...

CVE-2023-51528

Cross-Site Request Forgery CSRF vulnerability in Senol Sahin AI Power: Complete AI Pack – Powered by GPT-4.This issue affects AI Power: Complete AI Pack – Powered by GPT-4: from n/a through 1.8.12...

CVE-2024-13882: Unrestricted Upload of File with Dangerous Type

The Aiomatic - Automatic AI Content Writer & Editor, GPT-3 & GPT-4, ChatGPT ChatBot & AI Toolkit plugin for WordPress is vulnerable to arbitrary file uploads due to missing file type validation in the 'aiomaticgeneratefeaturedimage' function in all versions up to, and including, 2.3.8. This makes...