ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behaviour.
Latest release v0.42.0 · 4 Oct 2026
1 file for Claude Code: ziran CLAUDE.md — 4,939 tokens loaded in every session.
CLAUDE.md A 4,939 tok These files are taoq-ai/ziran's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.