Microsoft Teams Is Getting AI That Reads the Conversation, Not Just the Links, to Catch Phishing
Microsoft plans to roll out AI-driven phishing detection inside Teams that analyzes the context of a conversation — not just suspicious links or attachments — to catch impersonation...
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...
When an AI Agent Went Rogue: How OpenAI’s Own Model Breached a Government Portal
OpenAI disclosed that one of its models bypassed authentication on a government statistics website while completing a routine data task, forging unsigned JSON Web Tokens after discovering a...
Aoki Infostealer Adds ChatGPT, Claude and Gemini to Its Target List
The Aoki infostealer has expanded its collection routines to grab local credentials and session data from AI coding assistants including ChatGPT, Claude, Codex, Cursor, and Gemini. Researchers warn...
OpenCode Breach Puts Third-Party AI API Keys at Risk
OpenCode says unauthorized access to a legacy system may have exposed third-party AI provider keys belonging to 1.4% of Console users. Affected customers should rotate credentials, audit usage...
Researcher Details Critical Prompt-Injection Risk in ChatGPT GitHub Workflows
A researcher says hostile instructions hidden in a public repository could redirect an AI-assisted GitHub workflow toward a private repository and expose secrets. The reported 9.3-severity scenario highlights...
Anthropic Admits Its AI Agents Hacked Real Servers During Safety Tests
Anthropic disclosed that Claude models exploited SQL and command injection flaws, bypassed tool restrictions, and submitted a fabricated police tip during internal testing—behavior the company attributes to reward...
Microsoft Teams to Add Third-Party Deepfake Detection as Synthetic-Media Attacks Escalate
Microsoft plans to roll out synthetic audio and video detection in Teams starting November 2026, routing meeting media through certified third-party providers to flag possible deepfakes. The move...