The evidence behind the threat
Attackers are using AI to investigate systems, test weaknesses and pursue access. Defenders are also finding previously unknown flaws with it. These published reports show what that looks like in practice.
Reported attack
Anthropic estimated this share in an espionage campaign targeting roughly 30 organisations. It reported successful intrusions in a small number of cases. Humans chose the targets and directed key decisions; the AI also made mistakes.
Anthropic · November 2025 ↗Vulnerabilities found and fixed
Mozilla reported finding these flaws during an initial evaluation of Claude Mythos Preview. This was research on Firefox, followed by fixes shipped to users—a concrete example of defenders putting AI to work.
Mozilla · April 2026 ↗Controlled attack simulation
The UK AI Security Institute reported that GPT-5.5 completed the full chain in 2 of 10 attempts, from an initial network foothold to a protected database. Each attempt had a 100-million-token budget. The environment had no active defenders.
UK AI Security Institute · GPT-5.5 · 2026 ↗Our takeaway: use these capabilities to test your own defences, and revisit them as systems and models change. These are external findings in different settings, not EverBreach results or a prediction of your likelihood of being breached.
A new release can introduce a flaw. A more capable AI model can help uncover a weakness that was already there. Attackers can benefit from either. Security testing needs to revisit the routes into sensitive data, business processes and connected services.
Read articleThe aim is to simulate how an attacker moves through an agreed environment: from an ordinary account or public interface to access they should never have. Every demonstrated step should lead to evidence, a clear impact and a way to close the gap.
How it works
A useful assessment connects the technical weakness to what it lets someone do. The depth of testing is agreed for each engagement.
Identify the applications, APIs or infrastructure that matter, the roles to test and the actions that are allowed. Confirm the proposed work and access before testing starts.
In an attacker simulation, the question is whether an ordinary action can lead to unintended access. Use controlled accounts and test data to demonstrate the path without collecting real records unnecessarily.
Record the affected version, test setup and evidence. Distinguish a newly introduced flaw from an older weakness found during a new test. Attribute a model improvement only when the comparison supports it.
Give the responsible team the root cause, containment steps and permanent fix. Retest both the access that must be denied and the legitimate use that must keep working.
What is at risk
Access decisions happen across applications, APIs, storage and infrastructure. A page can look perfectly normal while the systems behind it expose data or bypass a business rule.
Authorized testing
An attacker simulation needs permission, a defined scope and a clear stopping point. These are agreed before any testing.
Identify the systems, accounts and actions permitted in the engagement. Third-party services need their own authorization where applicable.
Agree test accounts, synthetic records and stop conditions. A limited proof should establish the weakness without turning a test into bulk access to personal data.
Before testing, we explain the model provider, information sent to it, storage and retention. Sensitive evidence needs an agreed handling process.
Separate demonstrated access from possible wider impact. The report should show the reasoning and give your team enough detail to reproduce the result within the agreed scope.
FAQ
No. The project is aimed at security across applications, APIs and connected systems, for organisations of different sizes. The scanner currently implemented here is narrower: it checks public website configuration. We distinguish that starting point from the broader attacker simulations we are developing.
An AI-assisted test follows a possible attack path within agreed boundaries: what an account can access, which information it exposes and what that enables next. The sample scenarios show the intended depth of evidence. They are illustrative, not results produced by the current scanner.
A software change may introduce a weakness. A better model may find a weakness that earlier testing missed. These are different reasons to retest, and neither makes every new finding a zero-day or proves that AI alone caused the discovery.
Yes. The report is written for the people deciding what to fix and the people implementing it. That may be an internal security team, developers or an external provider. Each finding should identify an owner and a way to verify the change.
Scope, availability, price and delivery are agreed before you commit. Sending an enquiry is free and does not start a scan, reserve a slot or create an obligation to purchase.
Continuous testing and automatic retests after model releases are still in development. Current assessments and any follow-up checks are agreed individually.
First assessments
Tell us about your organisation and the area you want to assess. We will reply personally by email to discuss whether the pilot fits your needs.
Start with one agreed system or business workflow. Choose it around the data, access or process you need to protect.
What was tested, what was demonstrated, the possible impact and how to fix it. Coverage and limits are documented even when no issue is confirmed.
Review the evidence and priorities with us. Bring whoever will make the fixes: your developers, security team or external IT provider.
Repeat the agreed checks to verify the corrections. The proposal defines what the retest covers and when it can take place.
Before you commit, the proposal sets the testing scope, fixed price, delivery date and retest window. Your enquiry is free and does not start testing.
Before granting access, you will know who is responsible for the assessment, which model provider is involved and how the evidence will be handled.
Tell us which systems matter to your organisation. We will discuss the scope and the next step with you.
