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 ...
eWeek

Clean GitHub Repo Attack Exposes AI Coding Agent Risk

Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, ...
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.

一个CLAUDE.md霸榜GitHub第一，蒸馏自Karpathy，6万码农抄作业

一个毫无代码的文本，竟连霸GitHub热榜第一。Karpathy的编程神技被化作「AI紧箍咒」，让乱写Bug的大模型瞬间老实！ 就在刚刚，一个.md文件冲爆了整个GitHub！
Developer Tech

Mozilla shows Claude Code malware risk in clean GitHub repo

Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...
VentureBeat

Three AI coding agents leaked secrets through a single prompt injection. One vendor's ...

A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Security ...

Build 2026: Microsoft's MDASH exits preview with 100+ specialized threat-hunting AI agents

Build 2026: Microsoft's MDASH exits preview with 100+ specialized threat-hunting AI agents ...

Cursor now has a mobile app for guiding your coding agent on the go

Cursor has launched a new mobile app for remote oversight over coding agents.

Z.ai launches ZCode to challenge Cursor, Claude Code and GitHub Copilot in AI coding

Z.ai has launched ZCode, a free AI coding tool powered by GLM-5.2 that challenges Cursor, Claude Code and GitHub Copilot ...