Self-serve AI pentesting is now live

Barrion's AI pentest attacks your web app or API the way a real attacker would. It maps your attack surface, chains live requests to find what is genuinely exploitable, and reproduces every finding in an isolated sandbox before it reaches your report. Until now, kicking one off meant booking a call with us to scope it first.

Now any Barrion account can set up and start an AI pentest directly, with no call required, and the same release deepened the engine underneath it. You define the scope, pick a level, pay for the run in credits, and follow it live. The full report comes with it.

What is new

This release changed two things.

The first is access. Setting up a pentest no longer needs a call. A wizard in your dashboard walks you through the target, the credentials, and anything you want left alone, and nothing is sent until you approve it.

The second is depth. This release extends the engine's multi-wave attack chaining and broadens its authenticated testing, so a run digs further into your app than it did before. A run is paid for in credits before it starts, and you can follow its progress in your dashboard. The complete report, with proof and remediation for every finding, comes with the run: there is nothing to unlock afterwards. Whether you are a solo developer or an enterprise security team, that turns what used to be a scheduled engagement into something you can start yourself.

How a run works

Each engagement moves through five phases inside an isolated Kali sandbox you can watch in real time:

1. Scope and authorize: you set the target, its surfaces and credentials, and mark anything off-limits. The agent stays aggressive inside the scope and quiet everywhere else.
2. Recon and discovery: it maps hosts, endpoints, parameters, auth flows, and your stack before attacking anything.
3. Multi-wave attack: specialist agents work through injection, access control, authentication, API, and business-logic testing, carrying findings from one wave into the next.
4. Reproduce before report: every replayable finding is re-run in the sandbox. If it does not reproduce, it never reaches your report.
5. Report and retest: you get a ranked report with proof, remediation, and WSTG coverage as a downloadable bundle with a shareable PDF. Once a fix is in place, we retest the finding and confirm it is resolved.

You can watch the run live in your dashboard, and most runs finish within hours. At Standard and deeper levels, our security team reviews the results before the report is released, within one working day; a Light run releases its report as soon as it finishes.

Real attacks, not a scan

A scanner matches patterns and gives you a list of things that might be wrong. This works differently. Each run spins up a per-engagement Kali box with the tools a manual tester reaches for, including sqlmap, nuclei, ZAP, katana, ffuf, dalfox, and jwt_tool, and the agent reasons about your specific app as it goes. It confirms a bug from the response itself, whether that is a blind SQL injection showing up as a timing difference or an endpoint returning 200 where it should return 403.

By the time something reaches your report it has already been reproduced, with the request, the response, the affected surface, and the matching OWASP WSTG and CWE references attached. There is far less to wade through, because the maybes were filtered out before you ever saw them.

What it looks at

Coverage maps to the OWASP Top 10, the OWASP API Security Top 10, and all 97 WSTG v4.2 test cases, each with an evidence-backed status:

• Injection and web exploitation: SQL and NoSQL injection, XSS, command injection, SSRF, SSTI, XXE, CSRF, open redirects.
• Access control and authentication: broken access control, IDOR, privilege escalation, session and JWT flaws, multi-tenant isolation.
• API and business logic: BOLA and BFLA, mass assignment, excessive data exposure, rate-limiting gaps, business-logic abuse, file upload and path traversal, chained exploits.

The report ships with a full coverage matrix, so you can show an auditor or a customer exactly what ran and how each case came out.

Running it safely

Testing your own production app should not feel like a gamble, so every probe is rate-limited and non-destructive. The agent proves a finding by reading the response, not by writing or deleting data, and it only touches what you approved during setup. If you would rather start on staging, point it there instead. It runs against any environment you control and authorize.

When to run it

Run it whenever you need a real pentest. That covers the annual, audit-ready assessment for SOC 2, ISO 27001, or a customer security review, and it covers the moments in between too: when you ship a feature, before a launch, or any time a change makes you uneasy. Because it is self-serve and repeatable for a known number of credits, most teams stop treating a pentest as a once-a-year event and run one whenever the app changes.

It stands on its own as a full pentest. If your security program also brings in manual testers, Barrion makes every one of those engagements more productive: the OWASP Top 10, the API Security Top 10, and all 97 WSTG cases are already covered with reproduced proof, so no one starts from a blank page.

Try it

Create a free account, open Pentesting in your dashboard, and set up your first run. Setup takes a few minutes, then the agent goes to work and you can follow the run in your dashboard until the report lands.

Running a larger estate, want recurring pentests on a schedule, or need the scope and rules of engagement agreed up front? Talk to us about scope and we will put a plan together with you. It is the same testing engine underneath either way.