CyberStrike

Why we included this project

CyberStrike turns an existing LLM subscription into a command-line red team agent that can run penetration tests autonomously. It coordinates specialized agents across recon, web, network, cloud, and post-exploitation work, and ties findings to MITRE ATT&CK, OWASP WSTG, and CIS benchmarks so results are traceable to standard frameworks. The attack skill library is signed with Ed25519, which matters for teams that need to trust what the agent will execute, and the support for 150+ LLM providers means you are not locked into one model vendor. Post-exploitation coverage includes Linux, Windows, macOS, AWS, Azure, Kubernetes, and CI/CD environments, so it can handle cloud-native targets as well as traditional servers. Because this is an autonomous offensive tool, use it only against systems you own or have explicit permission to test.