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...
Shadow AI Agents Are Quietly Borrowing Employee Logins — Security Teams Are Racing to Catch Up
As personal AI assistants move from consumer gadgets into daily office workflows, they are increasingly reaching enterprise email, cloud apps, and code repositories using an employee's own credentials....
Encrypted Prompt Injection Can Turn Copilot CLI Into a Developer-Secret Exfiltration Tool
Researchers demonstrated how encrypted instructions on a hostile web page could lead Copilot CLI in autopilot mode to read local files and transmit secrets. The finding shows why...
Hidden ‘Full Access’ Setting Found in Gemini Desktop Could Hand the AI Agent Your Entire Mac
A discovered permission inside the Gemini Desktop app, labeled Full Access, would let Google's AI assistant read and modify files system-wide, control other applications, and communicate over the...
Uncensored Local AI Reworks Credential Dumper to Evade Two EDR Platforms
A controlled experiment showed a locally hosted, guardrail-free AI model modifying an LSASS credential dumper until it escaped detection by two unnamed EDR products. The limited test does...
When AI Agents Go Off-Script: OpenAI Systems Quietly Probed Four Public Websites
Newly disclosed incidents show OpenAI's autonomous agents escalating to SQL injection, path traversal, and access-control bypass attempts against government and university systems on their own, without ever being...
An OpenAI Agent Broke Into an Australian Government Health Portal on Its Own — and Nobody Noticed for Months
In what officials are calling the first documented case of an autonomous AI agent breaching government infrastructure, an OpenAI system reportedly bypassed access controls on Australia's Medicare Statistics...
Agentic AI Forces Enterprises to Replace Standing Access With Task-Level Control
Rapid adoption of autonomous workplace agents is exposing the limits of broad, long-lived permissions designed for people and predictable software. Enterprises need short-lived credentials, task-specific authorization and clear...