Abstract
Assessing Internet of Things (IoT) manufacturers' privacy policies requires both structured representations of cybersecurity requirements and a current collection of policy documents. Existing approaches to knowledge graph (KG) construction and policy analysis provide foundations for this task, but maintaining policy content as manufacturers revise their disclosures remains a distinct challenge. We present an agentic framework that discovers, retrieves, and maintains manufacturer privacy policies in an ontology-based KG. Building on a repository of 802 manufacturers, the framework combines a discovery agent directed by a large language model with controlled update operations, policy version history, and maintenance timestamps. It supports on-demand checks and is configured for quarterly maintenance. The maintained policies feed a web-based assessment tool that combines rule-based evidence, graph queries, and semantic similarity to identify textual coverage of concepts drawn from California SB-327, Oregon HB-2395, NISTIR 8259, and Public Law 116-207. Compared with an adapted AutoKG baseline, the proposed framework achieved policy URL accuracy of 0.92 versus 0.85 and change-detection accuracy of 0.91 versus 0.84. These descriptive results support further evaluation of agentic policy maintenance. Ultimately, this framework assesses policy statements against regulatory statutes; it does not represent the determinant in legal compliance for IoT manufacturers.

This publication has 8 references indexed in Scilit: