Intruder launches AI pentesting for faster validation

Intruder has launched AI Pentesting, now available to users on its Cloud, Pro and Enterprise plans.

The London-based cyber security company said the product uses AI agents to investigate scanner findings by interacting directly with a target, sending requests, analysing responses and probing for exposed data.

The agents are designed to validate issues often surfaced by vulnerability scanners, including injection flaws, client-side attacks and information disclosure risks. Intruder said the system uses methods employed by human pentesters and security specialists to assess whether a finding represents a real security problem.

The launch comes as security teams face growing pressure to respond more quickly to newly discovered weaknesses. Intruder cited its Security Middle Child Report, which found that 49% of security leaders ranked AI and automation as their top investment priority for 2026, while 42% of mid-market security teams described themselves as stretched, overwhelmed or consistently behind.

That has raised questions about the value of relying on annual or quarterly pentesting cycles when attackers can move much faster. Intruder said AI has cut the time needed to weaponise vulnerabilities from months to hours, leaving organisations exposed between formal tests.

"Pentesting has long been an essential component of any security program," said Andy Hornegold, Chief Security Technologist at Intruder.

"But in the age of AI, attackers can move faster than ever, the volume of vulnerabilities is growing, and exploit windows have shrunk from months to days to hours. The old playbook of quarterly or annual pentests has long been unfit for purpose. The threat landscape now requires a new approach focused on delivering the depth of a manual pentest on demand."

How it works

The first release focuses on issue-level investigations rather than full application assessments. When a scanner flags a potential weakness, the AI agent attempts to reproduce and examine it to determine its impact.

For injection issues, the agent tries to validate the flaw by reproducing scanner findings with error-based, timing-based and UNION-based techniques, among others. For client-side attacks such as clickjacking, it is designed to distinguish between pages that are deliberately frameable and those that pose a genuine risk.

For information disclosure findings, the agent reviews what data is exposed and assesses how an attacker might use it. If credentials such as login details or API keys are discovered, the system attempts to verify whether they are valid.

Intruder said this process is intended to cut investigation time from hours to minutes, reducing the manual triage required from security, IT and software development teams. It argued that this can help teams spend less time on false positives and more time on remediation.

Market focus

Founded in 2015, Intruder sells exposure management software aimed at organisations with lean security teams. The company says it now serves more than 3,000 customers worldwide.

The product sits within a broader market push to automate security work that has traditionally required human analysts. Vulnerability scanners have long offered frequent and relatively low-cost coverage, while manual pentests have typically provided deeper analysis at higher cost and lower frequency.

Intruder is positioning the new offering between those two approaches by automating the investigation and validation stages that often slow remediation work. That reflects wider demand from mid-market companies seeking more frequent scrutiny without the expense and scheduling delays of traditional testing engagements.

Users on eligible plans now receive AI Pentesting credits, with additional credits available for purchase. The current release covers issue-level investigations across findings identified within the Intruder platform.