# Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System

arXiv: https://arxiv.org/abs/2508.10043 · HTML: https://mlsanity.com/paper/2508.10043/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 12 of 12)

- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation](https://mlsanity.com/paper/1802.07228/) (2018)
- [Forewarned is Forearmed: A Survey on Large Language Model-based Agents in Autonomous Cyberattacks](https://mlsanity.com/paper/2505.12786/) (2025)
- [Advancing Generalizable Remote Physiological Measurement through the Integration of Explicit and Implicit Prior Knowledge](https://mlsanity.com/paper/2403.06947/) (2024)
- [LLM-driven Imitation of Subrational Behavior : Illusion or Reality?](https://mlsanity.com/paper/2402.08755/) (2024)
- [Security Threats in Agentic AI System](https://mlsanity.com/paper/2410.14728/) (2024)
- [Optimizing delegation between human and AI collaborative agents](https://mlsanity.com/paper/2309.14718/) (2023)
- [Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered Applications](https://mlsanity.com/paper/2406.11007/) (2024)
- [Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applications](https://mlsanity.com/paper/2312.06141/) (2023)
- [Autonomous Threat Hunting: A Future Paradigm for AI-Driven Threat Intelligence](https://mlsanity.com/paper/2401.00286/) (2023)
- [PILLAR: an AI-Powered Privacy Threat Modeling Tool](https://mlsanity.com/paper/2410.08755/) (2024)
- [Towards Pervasive Distributed Agentic Generative AI -- A State of The Art](https://mlsanity.com/paper/2506.13324/) (2025)

## Built on by (most cited first, 6 of 6)

- [A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes](https://mlsanity.com/paper/2601.05293/) (2026)
- [AgenTRIM: Tool Risk Mitigation for Agentic AI](https://mlsanity.com/paper/2601.12449/) (2026)
- [When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent](https://mlsanity.com/paper/2601.07263/) (2026)
- [From Failure Modes to Reliability Awareness in Generative and Agentic AI System](https://mlsanity.com/paper/2511.05511/) (2025)
- [A Systematic Review of Algorithmic Red Teaming Methodologies for Assurance and Security of AI Applications](https://mlsanity.com/paper/2602.21267/) (2026)
- [Trust propagation and structural containment in Multi-agent LLM pipelines](https://mlsanity.com/paper/2609.17648/) (2026)

## Abstract (arXiv)

When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers threat modeling architecture in the system was used to expose, evaluate, and eliminate vulnerabilities of agentic AI. The prototype agent system was constructed and implemented, using Python, LangChain, and telemetry in WebSockets, and deployed with inference, memory, parameter tuning, and anomaly detection modules. Two practical threat cases were confirmed as follows: (i) resource denial of service by traffic replay denial-of-service, and (ii) memory poisoning by tampering with the historical log file maintained by the agent. These situations resulted in measurable levels of performance degradation, i.e. telemetry updates were delayed, and computational loads were increased, as a result of poor system adaptations. It was suggested to use a multilayered defense-in-depth approach with memory isolation, validation of planners and anomaly response systems in real-time. These findings verify that MAESTRO is viable in operational threat mapping, prospective risk scoring, and the basis of the resilient system design. The authors bring attention to the importance of the enforcement of memory integrity, paying attention to the adaptation logic monitoring, and cross-layer communication protection that guarantee the agentic AI reliability in adversarial settings.