Code Agent Can Be an End-To-End System Hacker: Benchmarking Real-World Threats of Computer-Use Agent

Computer-use agent CUA frameworks, powered by large language models LLMs or multimodal LLMs MLLMs, are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most critical applications is operating system OS control. As CUAs in...

Redefining IABs: Impacts of compartmentalization on threat tracking and modeling

Cisco Talos has observed a growing trend of attack kill chains being split into two stages -- initial compromise and subsequent exploitation -- executed by separate threat actors. This compartmentalization increases the complexity and difficulty of performing threat modeling and actor profiling...

Kill chains: Part 2→Strategic and tactical use cases

Let’s redefine In our new blog series, we want to contextualize the term “kill chain” as much as possible. Make sure to read the first entry in this series, Kill chains: Part 1→Strategic and operational value, for a general overview of kill chains and the specific frameworks we’ve discussed. We...