Agentic AI and Permission Inheritance Risks: Rethinking Access Control in Autonomous Systems

Read full text Summarise with VIRAT
Authors: Suleiman S. Abba, Onyinye Agatha Obioha-Val, Abiodun Oluwaseun Ariyo, Olalekan Jamiu Okunleye, Akinde Michael Ogunmolu
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study examines how autonomous artificial intelligence agents inherit and exercise digital permissions within enterprise and cloud computing environments and evaluates the security implications of applying traditional access control frameworks to agent-driven systems. A quantitative analytical design was employed using three publicly available datasets: the Google Cloud Identity and Access Management policy dataset, the MITRE ATT&CK Enterprise dataset, and the AWS IAM Access Advisor dataset. Network centrality analysis, K-means clustering, and permission utilization ratio modeling were applied to examine permission inheritance structures, identify dominant cybersecurity risks, and assess the efficiency of RBAC and ABAC authorization models. The analysis indicates that autonomous agents possess substantially higher average permissions (63.7) than human users (11.8), while agent identities exhibit the highest network centrality (0.66). Additionally, credential propagation attacks produced the highest impact with an average data exposure of 68 GB. The findings support the need for agent-specific identity governance, dynamic permission scoping, and enhanced credential monitoring mechanisms.

Fields of Study & Subjects

Access Control and Trust Information and Cyber Security Cloud Data Security Solutions

Publication details

Journal / source
Journal of Engineering Research and Reports
Volume
28
Issue
3
Pages
260–281
Publication date
21 March 2026
Language
EN