545 Hackers Tested It First. Now XRanges for AI Scores Your Security Agent

A new system called XRanges for AI has been developed to evaluate the effectiveness of autonomous security agents. This system was tested by 545 hackers, who used it to assess the agents' ability to find bugs. The challenge with these agents is that their reports are often difficult to verify, as they provide confident findings but no clear way to distinguish real vulnerabilities from false ones. To address this, a manual review process is typically used, where a security expert checks each finding against the target system to determine its validity. The goal of XRanges for AI is to provide a more reliable way to measure the performance of autonomous security agents.