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

2025

Closed access Metadata (CSL-JSON)
DOI 10.51885/3134-8025_jics_2026_1_10
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

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.