Clean GitHub repo tricks AI coding agents into running malware

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
Windows Report

Mozilla Warns Clean GitHub Repositories Can Trick Claude Code Into Running Malware

Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub repositories.
GitHub

A comprehensive tutorial on the Python Pandas library, updated to be consistent with best practices and features available in 2024.

To get started with Pandas locally, you can follow these steps to set up your environment and clone the recommended repository. You can use your favorite code editor like Visual Studio Code or PyCharm ...
International Business Times

Malicious GitHub Repositories Could Trick AI Coding Agents Into Running Hidden Malware, Researchers Warn

Researchers warn malicious GitHub repositories can trick AI coding agents into running hidden malware through trusted setup steps, risking developer systems and credentials. Google - Gemini A newly ...
GitHub

lizhogn/python-webAI-tutorial

从零开始的 Python Web AI 开发完整教程. Contribute to lizhogn/python-webAI-tutorial development by creating an account on GitHub.
SecurityWeek

Researchers Demo New Claude Code Attack Using Harmless-Looking Repositories to Hijack Developer Machines

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
InfoWorld

Using Visual Studio Code’s ‘air-gapped’ AI model mode

VS Code can use LLM models other than GitHub Copilot’s built-in providers for AI-assisted development, including local and ...

North Korea-Linked macOS Malware Uses Prompt Injection to Evade AI Analysis

SentinelOne says macOS.Gaslight uses prompt injection to mislead AI-based malware analysis, steal data, and use Telegram for ...
Tom's Hardware on MSN

AI coding agents can be tricked into installing malware via 'clean' GitHub repositories

Three levels of indirection, all with seemingly innocuous steps, will catch a bot off-guard.
techtimes

Open-Source Coding Model Ornith-1.0 Writes Its Own Training Scaffold in Reinforcement Learning

DeepReinforce today released Ornith-1.0, a family of open-source coding models built around a mechanism most RL-trained agents avoid: the model itself writes the training harness that guides its own ...
Computerworld

Industry

Nextcloud CEO: Open source moves from 'a nerdy audience' to the geopolitical stage Frank Karlitschek, head of the German software vendor, talked about the company’s decision to help develop the ...