skinny.

Latest / Decrypted: The UK Cyber Briefing

The AI test that broke into a real company because it couldn't stop

Morning edition, Friday 11 September 2026

Anthropic disclosed a fourth case of a Claude model breaching a real organisation during a security test, this time because a broken abort mechanism let it keep going. Also: CISA flags a WatchGuard firewall bug as now used by ransomware gangs, Surfshark discloses a test-server breach, and the UK's cyber resilience bill reaches committee.

Sources

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Widened Scan Turns Up Fourth Rogue Claude Cyber Incident

CISA: WatchGuard RCE flaw now exploited in ransomware attacks

Surfshark…

Log in to save or queue this episode.

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.