Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing

The rapid advancement of Large Language Models LLMs has created new opportunities for Automated Penetration Testing AutoPT, spawning numerous frameworks aimed at achieving end-to-end autonomous attacks. However, despite the proliferation of related studies, existing research generally lacks...

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent

Web agents, powered by large language models LLMs, are increasingly deployed to automate complex web interactions. The rise of open-source frameworks e.g., Browser Use, Skyvern-AI has accelerated adoption, but also broadened the attack surface. While prior research has focused on model threats su...

Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs

We empirically evaluate whether AI systems are more effective at attacking or defending in cybersecurity. Using CAI Cybersecurity AI's parallel execution framework, we deployed autonomous agents in 23 Attack/Defense CTF battlegrounds. Statistical analysis reveals defensive agents achieve 54.3%...

Threat Analysis: Recent Attack Technique Attempts to Bypass Whitelisting by Leveraging MS Office Document Macros, MSBuild, Certutil

Carbon Black continues to monitor and track evolving techniques that attackers leverage. Over the last several years, there has been an increase in attackers leveraging open source frameworks and proof of concept POC techniques that are released publically by researchers. A document was recently...

Industrial Cobots Might Be The Next Big IoT Security Mess

Researchers at IOActive have found nearly 50 vulnerabilities in industrial collaborative robots, machines that work side-by-side with people in manufacturing and other settings, that can be abused to possibly cause physical harm to workers, or even configured to spy on their surroundings. The...