プロンプトインジェクションからMCPサーバ攻撃、RAGポイズニングまで、80種の攻撃手法に予防策・検知策・対応策を体系化した164枚の実務資料 AIコネクティブカンパニーのコーレ株式会社（本社：東京都新宿区、代表取締役：奥脇 真人）は、AIエージェントを標的とした攻撃手法80種を体系的に整理し、それぞれに予防策・検知策・対応策を付した調査資料「AIエージェント攻撃手法と対策一覧（2026年3月版） ...

In addition to rolling out patches to address two zero-days affecting SQL Server and .NET, Microsoft introduced Common Log ...

Vulnerability left ~246,600 sites exposed to data theft Fixed in version 4.1.0; WordPress urges immediate updates A popular ...

Security researchers Tenable found the flaws, dubbed LeakyLooker, which exposed sensitive data across Google Cloud environments, affecting those who are using pretty much any Looker Studio data ...

First of four parts Before we can understand how attackers exploit large language models, we need to understand how these models work. This first article in our four-part series on prompt injections ...

Ecommerce platforms represent one of the most consistently targeted areas of the modern digital estate. They process payment data, store personal information, integrate with logistics and marketing ...

Operational penetration testing is a process of simulating real-world attacks on OT systems to identify vulnerabilities before cybercriminals can exploit them, either physically or remotely. OT ...

CyberStrikeAI lowers the barrier to complex cyberattacks by combining AI orchestration, MCP integration, and more than 100 offensive tools into a single, public GitHub repository.