Attention: You are using an outdated browser, device or you do not have the latest version of JavaScript downloaded and so this website may not work as expected. Please download the latest software or switch device to avoid further issues.
| 16 Mar 2026 | |
| Written by Gabi Gerber | |
| Attacks & Threats |
A cybersecurity startup says its artificial intelligence agent needed just two hours to break into McKinsey & Company's proprietary generative AI platform, accessing millions of staff messages and thousands of files.
CodeWall published findings earlier this week, disclosing that it also could have rewritten the chatbot's core instructions after its agent exploited a SQL injection flaw.
The startup said its agent gained full read and write access to the production database underpinning McKinsey's AI platform Lilli, an internal platform the high-priced consultancy says could "rewire the way we operate." Roughly three quarters of the firm's more than 40,000 employees use it for strategy work, client research and document analysis. Read more...
Python scripts were used to test malware against endpoint detection and response agents from Sophos, CrowdStrike, and Windows Defender. More...
Attackers are using AI to dramatically reduce the time they need to develop a working exploit for a CVE, according to ne… More...
High-autonomy agents with broad permissions and unfettered access are a recipe for disaster, and enterprises need to act… More...
AI agents aren't black boxes — they're models interacting with software tools. The risk lies in their overlap. More...
SharePoint access often means access to the keys of the kingdom, something attackers and defenders understand all too we… More...
Python scripts were used to test malware against endpoint detection and response agents from Sophos, CrowdStrike, and Windows Defender. More...
Attackers are using AI to dramatically reduce the time they need to develop a working exploit for a CVE, according to ne… More...
High-autonomy agents with broad permissions and unfettered access are a recipe for disaster, and enterprises need to act… More...
AI agents aren't black boxes — they're models interacting with software tools. The risk lies in their overlap. More...
Four talks tracing the path from Principles to Practice in Trustworthy AI. More...
