ARCHITECTURE AND INITIAL PERFORMANCE EVALUATION OF A MULTI-AGENT SECURITY AUDIT TOOL IMPLEMENTED IN THE GO LANGUAGE

Abstract

This article presents the development and performance evaluation of Pentool, a multi-agent penetration testing tool implemented in Go using a microservices architecture. The system comprises four independent agents coordinated via the NATS JetStream message broker for asynchronous, scalable task processing. Experimental studies on port ranges from 100 to 30,000 show that while Pentool has higher overhead on small ranges compared to Nmap, its distributed architecture enables superior scalability and predictable operation (10–100 times lower time variability). Pentool achieves comparable or better performance than Nmap on larger port ranges (from 5000 ports), confirming the effectiveness of the multi-agent approach for extensive security audits. The system demonstrates near-linear horizontal scalability.