
ActBench
Code for paper "ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents"
ai-securityapi-security-testinglabs-practice+1
5

Code for paper "ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents"

Generates reproducible CORE network topologies from XML scenario files for cybersecurity training and experimentation. Provides Web GUI and CLI for…

Zero-trust sandbox for AI agents with kernel-level filesystem jail, transparent network proxy, and YAML-based policy engine to intercept and control…

Ephemeral microVM sandbox for AI agents with network allowlisting, secret injection via MITM proxy, and VM-level isolation. Boots in under a second,…