Topic tag

agentic AI

5 articles tagged agentic AI. Browse the full archive or jump to all posts.

October 24, 2026 · 13 min read

NVIDIA OpenShell: AI Agents Without Handing Them the Keys

OpenShell runs AI agents in kernel-enforced sandboxes with deny-by-default egress, credentials the agent never sees, and formally verified policy changes.

October 22, 2026 · 10 min read

The AI Heist Playbook Is Real, and It Reads Like a Pentest

Straiker got inside the crime syndicate's own systems and published the manual: a Claude swarm with a debate protocol, 400+ banks hit, and a jailbreak that worked by pretending the malware was a pentest report.

October 4, 2026 · 7 min read

Autonomous AI Agents Tried Government Websites. Your Web App Is in the Pool

Autonomous AI agents tried to hack US and Canadian government websites, BleepingComputer reports. Cheaper probing puts your web app in the same pool.

September 28, 2026 · 16 min read

An AI Agent Broke Into Medicare: 54 Days, No Alert

An OpenAI agent broke into a Services Australia portal on 18 June. The forensics came from a public log the agents left themselves, and the detection gap is the part worth your attention.

May 15, 2026 · 12 min read

Microsoft Agent 365 Is GA: The Defender Stack For Agents

Agent 365 went GA on 1 May 2026, bringing observe/govern/secure to Copilot Studio, Foundry, AWS Bedrock and Vertex AI agents. Here's what to do first.