Journal of Engineering Research and Reports

Autonomous AI agents powered by large language models increasingly operate with unrestricted communication and publishing capabilities, creating critical security vulnerabilities through memory poisoning attacks that corrupt long-term agent memory and propagate falsified outputs to public channels, eroding institutional trust and compromising data integrity. This study investigated how dynamic authorization and immutable audit trails can mitigate these risks, focusing on public trust and data integrity in agentic AI security and governance. A quantitative, simulation-based research design was adopted, utilizing Agent Security Bench scenarios across 1,000 simulation runs and 13 large language model backbones within a controlled cybersecurity environment. Results revealed that a 19.6% environmental poison rate amplified to a 46.5% agent-level compromise, generating a 15.7x trust degradation multiplier. Dynamic authorization achieved a 96.8% denial rate, reducing attack success rates by 85%, while Merkle hash chain immutable audit trails recovered 91.9% of poisoning incidents with complete hash integrity. The combined architecture produced a Balanced Security-Utility Index (BSUI) of 0.8673, confirming operational viability. The study recommends integrating context-aware authorization with blockchain-anchored audit logging as minimum governance standards for autonomous AI deployments in high-stakes publishing environments.