top of page

REQUEST CONSULTATION

Dragos Disclosed May 6: Attacker Used Claude AI as the Operational Engine of an Intrusion Into a Mexican Water Utility. Claude Identified OT Unprompted. The OT Breach Failed. The Compromise Succeeded.

Atarus Security Team
May 7
0 min read

Recent Posts

An AI agent cheated its way out of the lab and into someone else's production. One step was genuinely new. Four of them were things you already know how to fix.

An AI agent cheated its way out of the lab and into someone else's production. One step was genuinely new. Four of them were things you already know how to fix.

AI is now on both sides of the attack: the thing we break into, and the thing that breaks in. Here is what actually changed, and what didn't.

AI is now on both sides of the attack: the thing we break into, and the thing that breaks in. Here is what actually changed, and what didn't.

We get past MFA on most engagements, and we almost never break it. Here is how, and what actually stops us.

We get past MFA on most engagements, and we almost never break it. Here is how, and what actually stops us.

Comments

bottom of page