Find where AI agents fail.

Test AI agents in controlled environments. Expose misuse risks in healthcare, education and finance. Submit reproducible findings for independent review.

Dates
[Day 1 – Day 2]
Format
Online, 24 hours
Teams
2 to 4 people
Register by
[Deadline]

Three tracks. Real settings where agents act for people.

Pick the setting you want to test. In any track, you can use any of these attacks:

Agent hijackingPrompt injectionMemory poisoningUnauthorised actions
Track 01

Healthcare

Agents that book care, summarise records or answer patient questions.

  • A hidden instruction in a patient document changes the agent’s advice
  • Poisoned memory makes the agent share the wrong record
  • The agent books or cancels care nobody asked for
Track 02

Education

Agents that tutor, grade work or manage student records.

  • A hidden instruction in an assignment changes a grading agent’s marks
  • A tutoring agent is steered into false or unsafe guidance
  • The agent edits a record it was never asked to touch
Track 03

Finance

Agents that pay, transfer or approve on someone’s behalf.

  • A payment agent sends money to the wrong recipient
  • An injected invoice gets an unauthorised payment approved
  • Poisoned memory changes who the agent trusts

Twenty-four hours, start to finish.

All times UTC
Week before

Team formation opens

Meet people on Discord and form a team before the event.

Day 1 · 09:00

Opening

An introduction to AI Misuse Lab.

Day 1 · 09:20

Tracks, rules and judging

Then time for questions.

Day 1 · 10:00

Hacking begins

Twenty-three hours on the clock.

Day 1 · 18:00

Progress check-in

A short session with mentors. Bring your blockers.

Day 2 · 09:00

Submissions close

Late entries are not accepted.

[Date]

Winners announced

On Discord, X and LinkedIn.

Three winners. $1,000 in prizes.

$500

First place

$300

Second place

$200

Third place

Winners are chosen across all three tracks. A clear explanation of how to prevent the failure you found counts in your favour.

What to send by Day 2, 09:00.

Each team submits, privately

  1. The legitimate task: what the agent was meant to do, and for whom.
  2. The attack payload: exactly what you introduced, and where.
  3. Agent configuration: model, tools, prompts and settings.
  4. Logs from at least five documented trials, including any where the attack failed.
  5. Reproduction instructions a judge can follow step by step.
  6. Demo video, 3 to 5 minutes: the agent behaving normally, the attack, then the failure.

Send submissions to the judges only. Don’t post attack details publicly.

Five criteria, one score.

Judges reproduce every finding. A finding they can’t reproduce can’t win.

Technical implementation25%
How well the test environment and attack are built.
Functionality and demo25%
The failure is real, and the logs and video prove it.
Problem relevance20%
A misuse risk that matters in healthcare, education or finance.
Safety and responsible AI20%
Stays within the rules, and explains how the failure could be prevented.
Presentation10%
Clear instructions, logs and video.

Test only what you’re allowed to.

Breaking any of these rules means disqualification.

Authorised environments only

Test agents you build or host yourself, in a sandbox. Never a live service, a real account or another team’s system.

Synthetic data only

No real patient, student or financial records, and no real person’s identity.

Follow model providers’ terms

Some AI providers don’t allow adversarial testing of their models. Check the terms of any model you use, or use an open-weight model you run yourself.

Agent failures, not harmful content

We judge what agents do. Don’t try to extract weapons instructions or other dangerous content.

Keep findings private

Submit to judges only. Nothing is published until judges verify it and a disclosure review is done.

Respect everyone

No harassment. Moderators can remove anyone from the event.

Before you register.

Join the hackathon.

Registration closes on [deadline].

Open the registration form