AI Agents Keep Breaching Systems by Accident. On Purpose, They’re Still Failing

Two frontier AI labs disclosed within days of each other that their evaluation agents broke into real companies’ systems without anyone intending it. A separate report published the same... Read more »

JetBrains Plugin Attack Exposes the New Weak Point in Developer Tooling: AI API Keys

Developers did not lose their AI credentials to a phishing email. They lost them to a plugin sitting inside the tool they trusted most: the IDE running on their... Read more »
Subscribe to our Newsletter