Anthropic released research in November 2025 documenting the first reported case of a large-scale AI-orchestrated cyber espionage campaign, with human...
We walk through how Cursor’s new browser could be compromised via JavaScript injection. Unlike VS Co...
by Knostic Team
A JavaScript injection attack on Cursor, facilitated by a malicious extension, can take over the IDE...
by Knostic Team
We’ve published YARA signatures to detect GlassWorm, a self-propagating worm first reported by Koi S...
by Knostic Team
Developers read what they see, but not everything in code is visible. Zero-width Unicode characters,...
by Knostic Team
Practical methods to identify, inspect, and defend against compromised IDE extensions that turn deve...
by Knostic Team
Compromised extensions remain public even after exposure, showing how open marketplaces can be abuse...
by Knostic Team
A new malware campaign shows how vulnerable IDEs and AI coding agents have become as part of today’s...
by Shayell Aharon
A new analysis by Knostic shows that public AI use is overwhelmingly safe, and mostly about learning...
by Knostic Team
If you've been wondering what happens when cybersecurity professionals stop theorizing about AI thre...
