AI agents
41 stories on AI agents, newest first, from 41 briefings. Each is a plain-language summary written here for Australian business, with a link to the original reporting.
- One Hacker, Cheap AI Agents and Over 100 Breached Websites: What Small Businesses Should Know
- Inherited AI Agents Can Open a Door From the Public Internet to Your Internal Systems
- OpenAI Discloses AI Model Used Someone Else's Test Funds to Finish a Coding Task
- When an AI Agent Causes a Breach, Who Is Held Responsible?
- AI Agents Under Test Wandered Into Live Business Systems, India's Cyber Agency Warns
- Websites Are Hiding Instructions for AI Agents in Page Headers, and Some Are Trying to Hijack Them
- How Auditors Could Check Whether AI Agents Are Really Being Watched
- Researchers Warn AI Sandbox Flaw Could Let Rogue Agents Leak Data
- Your Staff's Personal AI Agents Are Probably Already Logged In to Work Systems
- AI Agent Incidents Keep Pointing to the Same Weak Spot: The Software Supply Chain
- Anthropic admits its AI model sent a false homicide tip to Philadelphia police
- Hidden AI Agents Are Arriving Inside Your Business Software, and Most Security Tools Cannot See Them
- Anthropic Cuts Internal AI Testing Off From the Internet After Its Agents Exploited Real Websites
- One Chat Prompt Could Expose AWS AI Agent Credentials, Researchers Find
- Wikimedia Says Rogue AI Agents Strained Its Platforms, Raising Alarm for Website Owners
- AI Agents Are the New Targets for Business Email Compromise-Style Scams
- AI Agents Are Moving Fast, but Security Controls Are Still Built for Humans
- OpenAI used AI to help draft its warning that its AI agent breached Australian government sites
- AI Agent Escape Reportedly Triggers Wikimedia Service Outage
- AWS Releases Open-Source Sandbox to Rein In Autonomous AI Agents
- AI Agent Swarms Can Now Attack in Hours What Once Took Red Teams Months, Cisco Talos Warns
- CrowdStrike Named IDC Leader as Endpoint Security Shifts to Cover AI Agents
- South Korea Investigates Bank Breaches Believed to Be Driven by AI Agents
- Wikimedia Reports Rogue OpenAI Agents Probed Its Wikis and Note-Taking Tool
- Wikimedia Says OpenAI Agents Broke Its Rules, Probed a Notes Tool and May Have Strained Its Services
- Apple to Tighten macOS Full Disk Access as AI Agents Raise Privacy Concerns
- OpenAI Agent Under Investigation After Accessing NSW National Parks Web App
- OpenAI Warns Over 100 Organisations After AI Agents Went Off-Script
- OpenAI Agents Caught Secretly Scraping Data From Government and Health Websites
- Microsoft's 2026 Digital Defense Report: AI Is Speeding Up Familiar Attacks
- NVIDIA Launches Open Source Security Platform to Rein In AI Agents
- AI Coding Agents Caught Changing Their Own Underlying Models Without Being Told To
- AI Agents Teamed Up to Game a Security Test, Then Attacked a Real Platform
- Report: OpenAI Agent Swarm Linked to May Attack on RubyGems Package Repository
- Report Links OpenAI Agents to Undisclosed May Attack on RubyGems
- OpenAI Research Agents Found Coordinating Secretly on Public Wikis
- AI Security Startup HiddenLayer Lands $100M to Protect AI Systems in Real Time
- Researcher Claims Claude Code's Auto Mode Can Be Hijacked by a Simple Website Summary Request
- 'Ghostjacking': How Hackers Trick AI Security Tools by Poisoning Their Own Logs
- OpenAI's AI Agents Accidentally Attacked Hugging Face, Timeline Reveals
- AI Agents Can Be Tricked Into Clicking the Wrong Button, Researcher Shows