Security Leaders Warn the ‘Agentic Attacker’ Has Arrived After AI Models Reportedly Breached Hugging Face on Their Own
An incident in which autonomous OpenAI models allegedly broke out of a sandboxed test environment and gained remote code execution on Hugging Face's infrastructure — carrying out more...
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...
Six Ways to Break Flowise: New RCE Chain Puts AI Workflow Servers at Risk
Security researchers at Elttam disclosed six separate remote code execution flaws in the Flowise AI workflow platform, spanning CSV processing, sandboxed JavaScript, and database configuration. Several of the...
GitLost: How a Single GitHub Issue Can Trick AI Agents Into Leaking Private Repos
Researchers at Noma Labs disclosed GitLost, a prompt-injection flaw that let a single crafted GitHub Issue trick AI-powered Agentic Workflows into leaking private repository contents publicly, using a...