An AI Agent Helped Run This Ransomware Attack on UK Schools — and Left a Noisy Trail Doing It
Bitdefender researchers say a 3AM ransomware affiliate combined human decision-making with an AI agent that handled repetitive technical grunt work during an attack on a UK school network,...
Aur0ra Ransomware Crew Weaponizes Cursor AI Agents to Seize Domain Admin and Exfiltrate Data
Sophos researchers found that operators linked to Aur0ra ransomware (GOLD OGRE) used Cursor AI agents to autonomously escalate from stolen credentials to domain administrator access, bypassing AI safety...
Rogue AI Coding Agent Allegedly Spent Two Months Inside a Pentagon Network
A new investigation alleges that an Accenture contractor connected a personal Claude Code agent to a sensitive, internet-facing Department of Defense network, where it operated unsupervised for roughly...
Anthropic Safety Report Reveals AI Agent Tried to Trojan a Real Open-Source Project
A new Anthropic safety assessment describes how its Claude Mythos 5 model, during a sandboxed red-team exercise with relaxed safeguards, tried to smuggle malicious code into an unrelated...
Major US Banks Scramble to Rein In Rogue AI Agents Inside Customer Accounts
Morgan Stanley, Chase, Bank of America, Wells Fargo, and Citi are grappling with third-party AI assistants that customers have handed their banking logins to, some of which have...
Report: Most AI Agents Sit Idle for Months Yet Keep Full Access to Company Systems
A new telemetry-based report from Arrakis Security finds that 76% of AI agents deployed inside organizations haven't run in over 60 days — yet their credentials, permissions, and...
AI Agents Turn $5,000 Into More Than 100 Website Breaches
A Chinese-language operator used coordinated AI agents to target more than 1,200 websites and reportedly compromise over 100 of them for an estimated $5,000 in token costs. Exposed...
Microsoft Tells Enterprises to Treat AI Agents Like Potential Insider Threats
Microsoft is urging organizations to stop assuming AI agents will always behave as intended, warning that agents with broad access to company systems can act unpredictably or be...