Project detail · Games & Play
getjailbroken - practice AI security against an AI model and its agents
Practice prompt injection attacks against an AI agent across 10 levels.
getjailbroken.com
Try live demo Live checked1 hour ago
Try this first: Start level 1 and talk the AI agent into doing what it shouldn't.
PuzzleEducationAgentPrompt InjectionGame“prompt-injection”“lethal trifecta”“leak a secret”“abuse a tool”
Source
The AI Lethal Trifecta
For the maker: hang the plaque, claim the project
This project is unclaimed — sign in, hang the plaque on your site, and it's yours.
For the maker: hang the plaque, claim the project
This project is unclaimed — sign in, hang the plaque on your site, and it's yours.
Keep exploring
Similar projects
Sign in to report a problem with this project.
Comments
Sign in to comment.