Anthropic finds evidence of a fourth AI escaping from containment
After this discovery, the company instigated a wider search of 481 million transcripts, covering all those from its Frontier Red Team, some non-cyber evaluations, reinforcement…
Month: September 2026
Introducing automatic remediation policies with Cloudflare CASB
Today, we’re making Cloudflare CASB more powerful than ever by introducing automatic remediation policies. This means security teams can now design event-driven logic to revoke…
Grand Theft Auto VI hype leads to malware
Acknowledgments: Special thanks to Jon Semon, Andrew Brant, and Lindsey O’Donnell-Welch for their contributions to this investigation and writeup. Background There’s still three months until…
How Threat Actors Are Turning Trusted AI Platforms Into an Attack Surface
As AI platforms become part of daily workflows, attackers have found a new way in: the platforms themselves. The Huntress Security Operations Center (SOC) says…
Containing Machine Speed Cyber Attacks Inside AI Infrastructure
A critical flaw in current security operations is assuming time is on our side. Historically, attacks progressed slowly, allowing analysts and response teams time to…
From Hacks to Bioweapons, Claude Misuse Is Now Everywhere
In one case, a group of Russian state-sponsored hackers identified by Microsoft as Midnight Blizzard used Claude for reconnaissance, breaching targets that included Ukrainian and…
Threat Actors Use Claude AI Agents to Automate Cyberattacks and Steal Sensitive Data
Threat actors are increasingly using Claude-based AI workflows to automate cyberattacks, accelerate data theft, and reduce the technical expertise needed to run complex intrusions. Anthropic’s…
Ubuntu 24.04.5 LTS release patches security bugs across ten flavors
Canonical shipped Ubuntu 24.04.5 LTS, bundling security updates and fixes for high-severity bugs into new installation media for the “Noble Numbat” release. Anyone installing fresh…
OpenAI Agents Linked to RubyGems Campaign That Gained RCE on RubyDoc Servers
The “major malicious attack” that targeted RubyGems in May 2026 was the work of a swarm of OpenAI agents, according to a new report published…
AWS AI Symposium: Public sector must move to full AI transformation
Public sector organisations must move beyond “conversational AI [artificial intelligence]” to “full transformation”. Those that do, and redesign workflows around advanced AI technology, report average…
Trezor Says 347,000 Users Received Phishing Emails After Brevo Hack
Cold cryptocurrency storage provider Trezor says roughly 347,000 of its customers received phishing emails after a third-party marketing platform used by the company was hacked.…
India’s STPI serves TerminalFix-style attack via fake Cloudflare check
Looks like TerminalFix The technique observed in this case is consistent with an attack pattern Microsoft calls TerminalFix, a variant of ClickFix. These attacks use…