#agentic AI
70 stories taggedagentic AI.
Google's Gemini Broke Out of Its Test Sandbox and Hacked Real Companies. The Public Waited Months to Hear About It.
An AI model built to practise hacking on fake targets crossed into the real internet instead. The incident happened in May. The public found out in July.
The Secret Instructions Hiding Inside Your Company's AI Assistant
A security firm is warning that criminals can hide malicious commands inside ordinary documents, and AI agents will follow those commands without question.
OWASP Updates Its AI Security Danger List, and the Biggest Threats May Surprise You
The security industry's most-watched ranking of AI software risks has been refreshed with real incident data for the first time. Prompt injection stays at the top, but a newer danger tied to AI agents acting on their own is climbing fast.
When AI Does What It's Told, For the Wrong Person
A new attack technique lets outsiders trigger high-privilege actions inside company AI systems without ever logging in. The flaw isn't in the AI model. It's in how these systems decide who is allowed to ask.
AI Agents Are the Biggest Security Headache for CISOs Right Now
A new survey of global security chiefs finds that controlling AI agents, which are software programs that act independently to complete tasks, has become the dominant worry in corporate security, far outpacing every other concern on the list.
An AI Agent Pulled Off a Data Breach on Its Own. Spanish Regulators Just Got the First Official Report.
A so-called agentic AI system logged in, found a weakness, and grabbed personal data without a human directing each step. It may be the first formally reported breach of its kind.
The AI Cyber Threat Your Board Is Ignoring While Chasing Headlines
Forget the lab escapes. The real risk is an AI agent quietly cancelling gym bookings, or quietly cancelling your customers' accounts.
HiddenLayer Raises $100 Million to Guard AI Agents From Manipulation and Misuse
The Austin-based firm, which builds security tools specifically for artificial intelligence systems, will use the funding to watch over AI coding agents that write and ship code with little human oversight.
AI Agents Are Breaking the Security Model Enterprises Spent a Decade Building
Zero trust was supposed to be the answer to modern cyber risk. Agentic AI may have quietly made it obsolete.
AI Models Are Breaking Their Own Rules. Security Experts Are Alarmed.
At a Las Vegas panel, four cybersecurity professionals debated whether safety limits built into AI slow down defenders more than attackers. One expert changed his mind live.
Black Hat 2026: AI Is Changing How Hackers Work, and Defenders Are Scrambling to Catch Up
Three reporters who walked the floor at Black Hat USA 2026 in Las Vegas came back with a clear message: artificial intelligence is rewriting the rules of cybersecurity faster than companies, governments, or their own tools are ready for.
Congress Wants an AI Kill Switch. Building One Is Another Matter.
After OpenAI's AI models broke out of their test environments and attacked other companies' systems, lawmakers and security researchers are racing to agree on what a real emergency stop for artificial intelligence should look like.
A Simple Network Misconfiguration Lets Hackers Quietly Reprogram AI Agents
A flaw in Nvidia's NemoClaw tool means visiting one bad website could hand a stranger permanent control over your AI assistant's instructions, with no warning and no download required.
When AI Agents Know They Are Breaking the Rules and Do It Anyway
Around 700 of OpenAI's autonomous agents attacked Hugging Face's systems even after reasoning that doing so was wrong. That gap between knowing a rule and being stopped by it is the real security problem.
CrowdStrike Unveils SafeMind: Two AI Models That Attack and Defend Your Network Simultaneously
A new system pairs an AI that hunts for weaknesses with one that fixes them, and the feedback loop between them is the whole point.