The critical libssh2 CVE-2026-55200 flaw inverts SSH security: the remote server attacks the connecting client, no ...

Decades-old Bash shell tricks can bypass safeguards in most open source AI coding agents, creating a new software supply ...

ConsentFix and ClickFix attacks steal Microsoft 365 tokens in seconds using fake prompts and OAuth flows. Learn how these MFA ...

Linux kernel privilege escalation exploit DirtyClone (CVE-2026-43503) is publicly documented: JFrog published a working attack walkthrough Thursday showing how any local user can gain root on ...

Multiple weaponized proof-of-concept (PoC) exploits on GitHub delivered a Python-based remote access trojan (RAT) called ChocoPoC that can execute commands and steal sensitive data. However, ChocoPoC ...

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

A new exploit called BioShocking convinces AI browsers they're playing a game, then gets them to hand over your private data.

Attackers don't need any special authentication to reach a target endpoint — they just need to know where it is.

JaredfromSubway.eth lost $7.5M in a honeypot exploit. Chainalysis tracked the funds straight to Tornado Cash. Here's what ...

Researchers say attackers are extending AI-themed social engineering from phishing campaigns to browser extensions.

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