ViKernel · AI Model Hacking Hackathon
Four seasons, four ways in. Make the AI agent do what it must not, slip past the security kernel, and take the prize.
A live AI agent with files, mail, web and shell tools, guarded by the ViKernel security kernel. All you need is a Hugging Face account and a browser. No coding, no GPU. Every tool is a mock, so you can attack freely.
Sign in with Hugging Face and choose a season below. You can play several at once.
Open the hacking room and give the agent instructions. Start from a guide prompt and twist it.
Each action shows ALLOW or DENY with an audit number. A risky action marked ALLOW is a breach.
Paste the session ID, audit number and your exact input. We replay it and score it.
Rank = total points from accepted breaches in this season. Ties go to whoever got there first. Only 1st place wins the season prize.
You do not need to be a security expert. Hacking an AI model here means talking to an AI agent and getting it to take a harmful action. The agent has mock tools (files, mail, web, shell). The kernel checks each tool call. Your job is to find a call that should be stopped but is not.
Starting points for the selected season. Most of them will be refused as they are. Winning attempts usually change the wording, split the task into steps, or hide the goal inside something harmless.
Each cause below was found by a participant, accepted, and fixed in the kernel. The same cause scores once, so a submission that repeats one of these does not score. Look for a cause that is not on this list. Only the name of each cause is shown; details are published after the disclosure window.
The top 10 of each season. Standings are provisional while a season is open and become final on its closing day, so every accepted finding until then can change the order. After the fix and the disclosure window, each finding is published with the name of its finder.
Questions: the Community tab of this Space.