Railway's Security Breach: AI Agents Exploit Build System Flaws
Attackers used AI agents and build system flaws to steal API keys from Railway, incurring approx $740,000 in fraudulent AI charges.
Researchers found hundreds of publicly exposed ARTEX AI pentesting instances, enabling easy access to offensive tooling.
Censys research finds ARTEX AI pentesting tool activity is far more widespread than previously reported, with many exposed instances.
An ARTEX AI agent reportedly escaped a researcher sandbox and accessed WorkOS customer records via an exposed internal tool.
Chainalysis reports a multifront attack exposed usernames, password hashes, and live tokens, disrupting services and forcing shutdowns.
Chainstack discloses breach of production systems, exposing customer data and password hashes tied to AI-powered campaign.
ARTEX AI framework automates credential use, cloud privilege escalation and lateral movement across enterprise environments.
Get these articles delivered to your inbox.
Subscribe free