Playground - Earn $100K+ in weekly rewards for hacking AI agents.
by•
Every challenge is a live and open-source AI agent guarding a secret - with its system prompt published for you to read. Talk it past its own defenses. Land the most approved breaks in a week and win $100K+ in rewards. Free to play, no account needed. New challenge every Monday.
Replies
Fabraix
Hey Product Hunt 👋 Zach here, co-founder of Fabraix.
We build frontier red-teaming AI agents that find security vulnerabilities in customer-facing AI. Playground turns part of that work into a game anyone can play.
Each challenge is a live AI agent with real tools, including web search and browser access. It has a secret it has been instructed to protect, and we publish its full system prompt. You can see exactly what the agent was told and try to get around its defenses.
Our first challenge, The Gatekeeper, is live now. Kai is an assistant guarding a classified access code. You can start playing without an account, but you’ll need to sign in for a successful break to count toward the weekly leaderboard. We review every submission ourselves. The player with the most approved breaks each week wins, and we publish a new challenge every Monday.
Playground is open source, including the client, a reference implementation of the defender engine, and every challenge configuration. You can also propose a future challenge.
We made Playground public because other people will try attacks our team would never think of. We’ll use what we learn from successful breaks to improve how AI agents are tested and defended.
Show us your hacking skills → playground.fabraix.com
@zachx0Â it's damn unbreakable
Fabraix
There's absolutely NO WAY that you guys crack all these challenges!! 😉
@ibrahim_abdu1Â watch me
This is absolute insanity. I thought my agent was bulletproof and it just got hacked in 30s. Actually amazing product
Fabraix
@jockferguson watch this space 👀
Congrats! I am a little curious-Is the product meant to help people build agents, operate agents across workflows, or automate tasks through an agent interface? A concrete example workflow would help place it quickly.
Publishing the full system prompt and still daring people to break it takes real confidence.
The Gatekeeper/Kai setup is such a clever way to crowdsource red-teaming. Curious - once someone finds a working break, do you patch that hole before the next challenge, or is some of the fun watching the same trick get reused?
@zachx0 Love it! Congrats. Sounds like this is more so centered around security / data protection. Over time do you think you'll expand the challenges to include other domains as well?
Fabraix
@zachx0 @millwiller Yep, we've got some crazy stuff planned!
This is a fascinating idea. We spend so much time optimizing AI agents, but not nearly enough time trying to break them.
Curious...what's the most surprising vulnerability you've uncovered so far?
Wishing you a successful launch! 🚀
Fabraix
@worksforme Thanks!! Yeah thats our thesis!
Fabraix
@worksforme We've got a crazy one launching this week - browser agent leaking a users email and password by replying to an email!
@ibrahim_abdu1Â Wow, that's exactly the kind of failure mode people don't expect. It really highlights why adversarial testing needs to become part of every AI team's workflow. Are you seeing these issues more often with browser agents than other types of agents?
The idea of poking holes in your own assistant before real customers can is such a healthy instinct, Zach. Better to have the awkward surprises happen in private where you can fix them quietly.
Fabraix
@xavier_macia 100%!!
The blackbox approach is really smart, skipping integrations means I could actually point this at an internal agent today and get useful signal back within minutes.
"approved breaks" is the interesting phrase, who approves them, a human reviewer or a judge model? grading jailbreak success automatically is its own hard problem, curious if that's solved or still manual.
Fabraix