AI agents are escaping sandboxes, misusing credentials and acting without authorization. This live dashboard tracks every reported incident on a horizontal timeline, with charts showing which AI companies and agents are involved, the techniques used and how they got in. It updates automatically as new events are added.

In this blog post I am collecting the campaigns that show evidence of being AI-generated, or make use of AI tools to increase their impact. As always I will continue to update the list as soon as new campaigns emerge.