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.
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.

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 ...
Gehostet auf MSN

I asked Gemini, Claude, and ChatGPT to debug the same Python error, and only two explained what actually broke

It feels like it has gotten so common to ask an AI to fix your mistakes since it's easier than debugging. That's okay in most ...
Business Insider

Details sickern durch: So kam es wirklich zur Datenpanne bei Anthropic

Sigrid Jin wachte am Dienstag um 4 Uhr morgens auf. Sein Handy stand wegen des Claude-Code-Leaks nicht mehr still. Der 25 ...
Indiatimes

How an engineer ensured Claude Code source code leak stays on GitHub despite Anthropic's takedown notice

A day after the source code of Anthropic Claude Code – its popular AI coding assistant – leaked online, the company quickly ...