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 ...

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 ...

Tenable Research has uncovered a series of security vulnerabilities in Google Looker Studio, dubbed "LeakyLooker," that allowed attackers to run arbitrary SQL queries on victims’ databases and ...

Two critical n8n flaws (CVSS 9.4, 9.5) enable RCE via expression sandbox escape and public forms, risking credential exposure.

Researchers at red-team security startup CodeWall say their AI agent hacked McKinsey's internal AI platform and gained full ...

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 ...

Cisco has handed security teams one of the largest ever patching workloads affecting its firewall products, including fixes ...

The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach ...