Before Asking AI for Anything, Malicious Code Ran. Claude Code Tampering and 'The Day AI Became an Approver'—A Week That Changed Trust in Development, YNT Works AI SIGNAL ...

When developers ask AI to perform tasks, a screen sometimes appears to confirm what is allowed to be executed.Whether to modify files. Whether to run commands. Whether to connect to external services.
cyberpress

Microsoft Warns of Trojanized Claude Code Extension Planting Persistent SSH Backdoor

Microsoft has warned that a trojanized Claude Code extension distributed through Cursor’s marketplace attempted to install a ...
orcarouter.ai

ChainDrop: valid provenance in 400+ npm packages, and Claude Code hooks that need no npm install

On 4 August 2026 a stolen keyv GitHub account pushed malware to main and the project's own CI signed it. The ChainDrop worm ...
Help Net Security

Researchers broke the browsers built into VS Code, Cursor, Copilot, Codex and Claude Desktop

AI assistant browser vulnerabilities in VS Code and Codex let one file read a developer’s whole disk. Both tools are still ...
cyberpress

Hackers Hijack 42 GitHub Repositories to Plant Malware Traps for Claude, Gemini, and Cursor Users

Attackers planted execution hooks targeting Claude, Gemini, Cursor, and Visual Studio Code, turning routine development ...