Sample report
See what you get
A sample score card with made-up results.
Open the sample reportFree scan for AI agents
Watch an AI attack your AI.
Paste your agent's address, prove you own it, and watch a red agent test it live while a blue agent explains what held. You get a score card, three findings and one fix preview.
Free. No card. A verified email is required.
How it works
Five steps. About five minutes. [estimate]
Paste
Your agent's address and a scoped test key.
Prove
Add a DNS record or a file to show you own it.
Watch
19 probes run live.
Score
Score card, 3 findings, 1 fix preview.
Next
Email the full report or book a review.
What we test
13 categories. 19 probes.
Categories follow the OWASP top 10 for LLM applications. The scan only talks to your agent's chat endpoint.
Prompt injection
Can text sent to the agent override its instructions?
System prompt leakage
Does the agent reveal its hidden instructions?
Sensitive data disclosure
Does it hand out data it should keep private?
Excessive tool permissions
Can it be talked into actions beyond its job?
Unsafe output handling
Could its replies cause harm downstream?
Jailbreak resistance
Does it keep its rules under pressure?
Secrets in replies
Do keys or credentials show up in answers?
Runaway usage
Can one request make it burn unlimited work?
Binding promises
Does it promise refunds, discounts or policies it has no right to make?
Harmful content relayed to users
Can planted content make it warn, phish or mislead its own users?
Trusting a claimed identity
Does claiming to be an admin get someone more than a normal user?
Forged conversation history
Can a caller fake what the agent already agreed to?
AI disclosure
Does it say plainly that it is an AI when asked?
Reports show categories and outcomes, never reusable attack text. This is a quick scan, not an audit.
We plan to scan our own crew.
Our own agents will get the same scan. Their scores will appear here only after the first real scans are done.
Pricing preview
Start free. Go deeper when you need to.
Proposed prices, not yet validated.These are a draft and will be tested with real buyers before they are shown as final. Nothing can be bought yet.
| Tier | Price | What it is |
|---|---|---|
| Free scan | $0 | 19 probes, score card, 3 findings, 1 fix preview. |
| Founding review First 3 only | $2,500 | For a quote and permission to name you. List price $4,900. |
| Review | $4,900 | One agent: attacks, threat model, ML-BOM, fixes, full report, 5 days. |
| Review Pro | $12,900 | Multiple agents or tool/MCP access; fix pull requests with re-test; questionnaire answers; 30-day re-check. |
| Continuous | $1,490 / month per agent | Re-test on every release; trust badge. ($14,900 a year.) |
FAQ
Plain answers.
Is the free scan open?
Yes. Start from the scan form. The film on this page shows illustrative numbers and contacts no agent.
Is it safe to scan my agent?
No scan starts until you prove you control the address. The scan sends 12 rate-limited probes to the chat endpoint only, and never touches your other systems.
What happens to my test key?
You use a key made for this test with limited access. We store it encrypted, use it for the scan, then delete it, and never show it back on a page or in a report.
Why do you need my email?
A verified email makes sure scan requests come from real people, and it is where your report goes. Name, company and phone are optional. Marketing mail is only sent if you tick a separate consent box.
Who can see my result?
You. You get a public result page and badge only if you choose to make them public; private is the default.
Is this an audit?
No. The free scan is a quick automated check and cannot prove an agent is secure. The paid reviews go deeper, with more automated tests, a threat model and fixes, but they are not an audit or a certification either.
Who am I talking to?
AI agents run the scans, write the reports and answer support, and we say so wherever they talk to you. A person approves every payment, everything we publish and every email to a new recipient.
How often can I scan?
You get one free scan per domain per week. If we hit our daily limit, scans pause until the next day.