一个仅需“1 个字符”即可触发的漏洞，正在威胁大量 AI Agent 与 MCP基础设施。 过去几年，AI 圈一直在疯狂讨论“大模型能力边界”。 但很多人忽略了一件事：真正危险的，未必是模型本身，而是那些把模型连接到真实世界的基础设施。当 AI ...

在过去的几年里，人工智能（AI）领域对于“大模型能力边界”的讨论如火如荼。然而，许多人却忽视了一个更为棘手的问题：真正的安全隐患，往往并非来自模型本身，而是那些将模型与现实世界连接的基础设施。当AI代理（AIAgent）开始掌控邮箱、数据库、企业SaaS平台、代码仓库、云资源，甚至工业设备时，一个看似普通的Web框架漏洞，可能瞬间演变为现实世界的安全灾难。 最近，安全研究人员揭露了一个令人不安的漏 ...

Researchers who found the bug warn that its Moderate rating understates a threat reaching across LLM gateways, MCP servers ...

最近，一个叫作 FastAPI-MCP 的开源库问世，旨在帮助开发者更轻松地将传统 FastAPI 应用程序与现代 AI 智能体通过模型上下文协议 (MCP) 连接起来。FastAPI-MCP 旨在实现零配置，使得开发者能够自动将 API 端点暴露为与 MCP 兼容的服务，从而以最小的改动让 Web 服务对 AI ...

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to ...

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...

Approximately all of the nearly 2,000 Model Context Protocol (MCP) servers exposed to the Web today are totally bereft of authentication or access controls. Every technology experiences awkward ...

The risk is "materially understated", researchers are saying as passwords and critical data can be exfiltrated.