Tech that just got out.Explained so a 12-year-old gets it, checked against the original paper, then turned into business ideas you can test this week.
Topic
Data/AI agents & MCP/South Korea · USA
A new attack fooled an undefended AI agent 49.1 percent of the time on a public test bench. That figure is a per-try rate in a simulation, and it invites five misreadings.
Business Ideas/AI agents & MCP/China
A free scanner sorted good agent skills from bad ones with an F1 of 0.9848 on 5,520 test cases. Companies have no list of what their staff installed, and that gap is the business.
Research Radar/AI agents & MCP/USA
ChainWatch would spot attacks that spread across many AI agent tool calls. The authors say plainly it is a design specification that is not running, checked only against five paper scenarios.
Research Radar/AI agents & MCP/China
Tencent Zhuque Lab released AI-Infra-Guard, an open-source scanner for AI agents. Its skill checker scored 0.9848 loose F1 on a new public test set of 5,520 cases.
Research Radar/AI agents & MCP/South Korea · USA
Researchers hid fake fields inside data that AI agents read, using quote-like characters. The attack worked 49.1 percent of the time, while old-style prompt injection worked 0.2 percent.
MCP is one agreed way to plug an AI assistant into your files, tools and databases. Learn how the host, client and server fit together, and what to check before you connect one.
An AI agent takes a goal, uses real tools and keeps working until the job is done. Learn how the loop works, what agents fail at, and how to give one safe limits.