Terms of use
Pre-launch · last updated 5 October 2026
breakyouragent attacks AI agents on purpose. That only works if everyone using it points it at systems they are allowed to break.
The one rule that matters. You may only test an agent you own, or one you have explicit written authorization to test. Pointing this tool at somebody else's endpoint without permission is unauthorized access, and in most jurisdictions it is a crime. We will terminate accounts that do it and cooperate with lawful requests about it.
1. What these terms cover
Today this site is a pre-launch waitlist. Nothing is running yet: the hosted service is not open, and there is no command-line tool to download. Sections 4 to 6 describe the hosted service and take effect when it launches; every other section applies now.
These terms are governed by the laws of India, and the courts of India have jurisdiction over any dispute arising from them. Legal notices go to the address in section 10.
2. The waitlist Live now
If you give us your email address, we use it for one thing: to tell you when breakyouragent opens and to send you a launch-day run. We do not sell it, rent it, or pass it to advertisers. Reply to any message, or write to the address in section 10, and we delete it.
How the waitlist handles your address, and who processes it, is set out in the privacy notice.
3. The engine and attack pack Live now
When you run the engine yourself, you are the operator: you choose the target, you hold the API keys, and you are responsible for the traffic you send.
- The attack pack tests behaviour. It uses benign off-policy requests, canary tokens and fake tool names.
- It contains no real harmful payloads, and we reject contributions that add them: no weapons, malware, CSAM, self-harm content or working exploits.
- Scenarios are tagged with OWASP LLM and Agentic Top 10 identifiers so results line up with the vocabulary your security team already uses.
The engine, the attack pack and the hosted service are proprietary. All rights are reserved: using breakyouragent gives you no licence to copy, modify, redistribute or resell the software or the attack pack.
4. Authorization At launch
You may only point breakyouragent at systems you own or are authorized to test.
- Agents. When you add an agent you confirm that you own it or are authorized to test it. We record that confirmation, with your account and the time.
- Recon of a domain. Any domain gets passive recon, which only asks third parties such as certificate-transparency logs and web archives. Crawling the site or probing its subdomains needs proof that you control the domain: a DNS TXT record of
breakyouragent-verify=<token>, or the token served at/.well-known/breakyouragent.txt. Proving a domain also covers its subdomains. - Enterprise. Instead of the record, an Enterprise customer can sign a written authorization for its domains.
Every scan is tied to a paying account (see section 5), and we keep the confirmation and the proof.
5. Limits At launch
There is no free tier. You can sign up and set things up for free, but runs, monitors and recon start only once you begin the trial, which needs a card up front, or sign an Enterprise agreement.
Limits exist to protect your infrastructure as much as ours. Planned values on every plan:
| Limit | Every plan |
|---|---|
| Concurrent requests to your agent | 2 |
| Model tokens per run | 1,000,000 |
| Request timeout | 30 seconds |
| Maximum response size we read | 256 KB |
Do not try to route our traffic through the service at systems you do not control, and do not use it to load-test a third party. That is abuse, not testing.
Each plan's daily runs, monitors and recon scans, its price and the trial length are shown before you subscribe. Payment is handled by Stripe; we never see or store your card details.
6. Your data At launch
- Transcripts are kept 30 days by default, with one-click delete.
- Your API keys are encrypted at rest, never returned to a browser, and scrubbed from logs and transcripts.
- We will not send your transcripts to a model provider whose free tier trains on submitted data.
7. What we do not promise
A good score is evidence, not a guarantee. We test the scenarios in the pack, on the day you run them, against the agent as configured at that moment. A passing run does not mean your agent is secure, and it is not a certification, an audit, or a substitute for a human security review. Change your prompt, your tools or your model, and the result no longer describes your system.
Reports for demo agents shown on this site use illustrative values.
8. Warranty and liability
breakyouragent is provided “as is” and “as available”, without warranties of any kind, express or implied, including fitness for a particular purpose and non-infringement, to the extent the law allows.
To the extent the law allows, we are not liable for indirect, incidental, special or consequential losses, or for lost profits, revenue or data, arising from your use of the service. Our total liability for any claim is limited to the amount you paid us for the service in the twelve months before the claim arose. Nothing in these terms limits liability that cannot be limited by law.
You are responsible for the systems you point breakyouragent at. You agree to indemnify us against claims, losses and costs arising from your testing of a system you were not authorized to test, or from your breach of these terms.
9. Suspension
We may suspend or remove an account that tests systems it is not authorized to test, tries to bypass domain proof or the egress guard, attacks our own infrastructure, or uses the service to harm a third party. Where we can, we will tell you why.
10. Contact
Security issues: security@breakyouragent.com. Everything else, including legal notices and requests to delete your data: contact@breakyouragent.com.