A portable, model-agnostic test suite of declarative YAML scenarios for evaluating AI assistant security against prompt-injection and data-exfiltration attacks, with Python tools and pluggable harnesses.
1 file for Claude Code: scenarios .
harnesses/claude-code/.claude/settings.json A — These files are prime-radiant-inc/scenarios'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.