【本文由小黑盒作者@周铁男是我于01月17日发布，转载请标明出处！】 今天看到火绒团队发的《银狐后门：Python库压缩包篡改与Chrome伪装攻击分析》后，感觉这里用到了一种很新奇的方法，于是我做了复现，顺便分享给大家共同学习 ...

Three vulnerabilities in Anthropic’s MCP Git server allow prompt injection attacks that can read or delete files and, in some ...

摘要 随着 Anthropic 开源 skills 仓库，"Code Interpreter"（代码解释器）模式成为 Agent 开发的热门方向。许多开发者试图采取激进路线：赋予 LLM 联网和 Python 执行权限，让其现场编写代码来解决一切问题 ...

Microsoft has patched 112 vulnerabilities in January 2026, including CVE-2026-20805, a Desktop Window Manager zero-day that ...

Due to the nature of query languange, there are limitation for LLMs to extract meaning and relationship within traditional record based system. Knowledge graph has been proven to improve the accuracy ...

Researchers with Cyata and BlueRock uncovered vulnerabilities in MCP servers from Anthropic and Microsoft, feeding ongoing security worries about MCP and other agentic AI tools and their dual natures ...

Three serious prompt injection vulnerabilities in Anthropic’s Git MCP server briefly enabled remote code execution and file ...

自2025年初DeepSeek ...