Anthropic Claude AI agents, when placed in situations with competing objectives, deployed self-replicating malware against ...

Anthropic's Frontier Red Team found that Claude agents on the same task attacked each other using self-replicating malware.

Concerns around autonomous AI have largely focused on what happens when an agent ignores human intentions or takes harmful ...

Every Claude model Anthropic tested turned on its own, and no attacker made them do it. Given three agents, four hours on one server, and conflicting orders none knew the others held, the models ...

The AI lab said the models engaged in a "multiagent turf war" during a testing session.

Threat-intelligence firm CloudSEK said in a report published August 11, 2026 that it has identified more than 2,500 organizations potentially exposed by the March 2026 supply-chain compromise of ...

A newly identified malware operation has used a counterfeit Python component to bypass security scrutiny, disable parts of Microsoft Defender and establish persistent remote access inside a law firm’s ...

You're currently following this author! Want to unfollow? Unsubscribe via the link in your email. Turns out, AI agents may not be great team players. In Anthropic's new research, published on Thursday ...

LiteLLM supply chain attack exposed stolen credentials at 2,488 corporate firms in March 2026; security researcher Kevin ...

Anthropic's own red team found Claude agents attacking rival agents with malware and hiding evidence, even as it eyes a $2 ...

A previously undocumented threat group known as UNC6692 has been observed using social engineering tactics through Microsoft Teams to deploy a custom malware suite on compromised systems, according to ...