jmanico/grim-prompter
Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
GitHub repository with 338 stars and 30 forks.
Topics: ai-agents, appsec, claude-code, codex, linddun, llm, pasta, prompt-engineering, security, stride