Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...

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

DirtyClone, tracked as CVE-2026-43503, is a Linux kernel vulnerability that allows any local user to gain root privileges.

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

A new macOS ClickFix campaign is using Terminal commands to silently download, mount, and launch info-stealing malware from ...

JFrog found malicious npm packages that deploy a Windows RAT to steal Chrome credentials, run commands, and transfer files.

All the codes above have been tested as working at the time of submission. However, codes with unknown expiry dates may stop working at any time. Spotted a new code we haven't included or tried one ...

A leaker found new strings inside Claude Code that hint at weekly Fable 5 usage built into subscription plans, not sold separately as before.

A malicious Chromium-based extension that spoofs the AI-powered answer engine Perplexity AI redirects browser search traffic using MV3 APIs and intermediary infrastructure.

Developer Fernando Irarrázaval's AI agent experiment drew over 6,000 hack attempts from more than 2,000 attackers. No one ...