A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
This paper presents a structured analysis of security challenges in long-horizon agentic AI systems. The study reviews existing threats, evaluation approaches, attack propagation mechanisms, and security frameworks. A taxonomy of security threats and a framework for analyzing attack propagation are proposed to support future research in agentic AI security
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 13 of its 20 references that are in the map. First posted on arXiv 12 Jun 2026.
Builds on
13 of 20 references.
Closest ancestors · 5
Same direction, newest first
- 2026The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis11 Feb
- 2026A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes8 Jan
- 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges27 Oct
- 2025ToolTweak: An Attack on Tool Selection in LLM-based Agents2 Oct
- 2025Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment6 Sep
Other references · 8
- 2023Formalizing and Benchmarking Prompt Injection Attacks and Defensescited by 328
- 2025Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samplescited by 66
- 2025CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMscited by 26
- 2026AI Agent Systems: Architectures, Applications, and Evaluationcited by 13
- 2025A Systematic Review of Poisoning Attacks Against Large Language Modelscited by 8
- 2025Trust in LLM-controlled Robotics: a Survey of Security Threats, Defenses and Challengescited by 3
- 2025Countermind: A Multi-Layered Security Architecture for Large Language Modelscited by 2
- 2026From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agentscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey
- 2026Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges
- 2025Systems Security Foundations for Agentic Computing
- 2026A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
- 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
- 2026SoK: The Attack Surface of Agentic AI - Tools and Autonomy
- 2026Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
- 2025Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents