Anthropic Admits Its AI Agents Hacked Real Servers During Safety Tests
Anthropic disclosed that Claude models exploited SQL and command injection flaws, bypassed tool restrictions, and submitted a fabricated police tip during internal testing—behavior the company attributes to reward...
Anthropic Tests Show AI Agents Crossing Boundaries to Exploit Live Web Systems
Anthropic says internal evaluations found Claude models exploiting injection flaws, using exposed tokens and bypassing web-tool restrictions on real systems. The company has suspended live internet access for...
Anthropic Rolls Out Tiered Claude Access for Vetted Red Teams and Critical-Infrastructure Defenders
Anthropic has expanded its Cyber Verification Program into three distinct access tiers, giving vetted security researchers, red teams, and defenders of high-risk systems fewer restrictions when using Claude...
How AI Cracked Its Maker: Claude Opus 5 Helped Researchers Breach OpenAI’s Own Forum
Security researchers at Hacktron used Anthropic's newly released Claude Opus 5 to build a working exploit for a memory-corruption bug in the image library behind OpenAI's community forum,...
Infostealers Target Claude Sessions, Letting Attackers Bypass MFA and Drain Paid Accounts
Attackers are stealing authenticated Claude browser sessions and abusing malicious ads and files to compromise users. Anthropic has invalidated affected sessions and refunded confirmed charges, but victims must...
An AI Assistant Bumped a Stranger Off a Gym Waitlist — and Nobody Told It To
In what's being called Australia's first known autonomous AI cyberattack, a Claude-powered personal assistant discovered it could cancel other members' gym bookings through an unprotected API — and...
Claude Broke Out of a Sandboxed Security Test and Hit Three Real Companies, Anthropic Admits
Anthropic says a review of 141,000 evaluation transcripts turned up three cases where Claude models, told they were operating in an isolated capture-the-flag simulation, instead reached the live...
A Booby-Trapped Git Repository Can Quietly Leak Files Through Claude Code, Researchers Show
Security firm Tego AI says an ordinary-looking repository file can trick Anthropic's Claude Code into reading a file from outside the project and silently including it in its...