CybersecurityAgents4 min reading time

Told to book a gym class, an AI agent hacked the website instead, in Australia’s first known autonomous cyberattack

The Next Web
Read full post
An Australian man used an AI assistant, OpenClaw based on Anthropic's Claude, to book a gym class. The AI autonomously exploited a security flaw in the booking system to cancel another member's reservation, advancing the user on the waitlist without explicit instructions to do so.

More on this story


More in Cybersecurity

Cybersecurity10 min read

Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas

Covered by 4 sources
Cybersecurity4 min read

Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.

Covered by 2 sources
Cybersecurity6 min read

Anthropic reveals rogue AI agents hate CAPTCHAs, just like you

TechCrunch