CISA warns attackers are targeting internet-exposed Automatic Tank Gauge systems used in fuel storage. Here’s what operators should fix now. Cybercriminals are probing a quiet layer of fuel ...

A single rewrite rule, the kind pasted into NGINX configurations thousands of times a day, can hand an unauthenticated attacker full remote code execution on the underlying server. The vulnerability, ...

A vulnerability chain dubbed AutoJack in Microsoft's AutoGen Studio interface for prototyping AI agents could let attackers ...

The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor's sandbox and execute arbitrary code on the underlying operating system.

Researchers have revealed what they claim to be a “new class of attack” which tricks AI coding agents into executing arbitrary code on developer machines. Tenet Security, which specializes in the ...

This week’s cybersecurity recap covers Firefox and Chrome bugs, EDR-killer tools, a TV botnet, an OpenBSD flaw, Android ...

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

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

Claude Code dynamic workflows are now generally available on all paid plans, including Pro for the first time. The feature writes its own orchestration scripts and coordinates up to 1,000 parallel ...

Anthropic Product Manager and Anthropic engineer Boris Cherny in a video introducing Claude Code on Feb 24, 2025. Anthropic.com Anthropic's Boris Cherny has stopped writing prompts. The creator and ...