Detectify AB has introduced Agentic Tooling to enable artificial intelligence agents to verify potential vulnerabilities within live applications, with further coverage provided by Silicon Angle.
The new suite addresses the growing issue of AI-generated security reports that often contain false positives or fabricated evidence. Detectify reports that approximately 80% of findings from AI-driven static application security testing tools are noise, creating significant overhead for development teams. To combat this, the company launched a Security Ledger that records the specific evidence behind each test, allowing organizations to distinguish between verified threats and unsupported AI conclusions.
The tools integrate with existing AI agents via the Model Context Protocol or a command-line interface, utilizing Detectify’s established testing engines and payload assessments. By employing loop engineering, the system automates the testing process, triggering workflows from code scans or bug bounty reports.
Chief Executive Rickard Carlsson noted that the goal is to provide proof that an agent cannot fabricate, ensuring that security teams can trust their automated systems. This release follows the company’s previous efforts to automate vulnerability testing, building on its existing infrastructure to improve cyber hygiene across enterprise environments.
Source: Silicon Angle

