A Survey on Agentic Security: Applications, Threats and Defenses
cs.CL, cs.AI, cs.CR
Submitted: 2025-10-07
Updated: 2026-10-31
Comments: Transactions on Machine Learning Research (TMLR) 2026
Code: https://github.com/kagnlp/Awesome-Agentic-Security
License: http://creativecommons.org/licenses/by/4.0/
The gist: In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses.
Terminology
Abstract
In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses. We provide a comprehensive taxonomy of 274 papers that covers red-teaming, blue-teaming and domain-specific applications, attack surfaces on agentic systems, defense techniques, and both offensive and defensive evaluation frameworks. For each pillar, we first discuss the literature around the taxonomy and then perform a quantitative analysis to understand the patterns across these works. For the applications, we show their security-lifecycle coverage map, compare between red-teaming and blue-teaming agents, and analyze the adversarial use of red-teaming applications. On the threat side, we analyze the entry points and agent-loop stages that attacks target, their specificity to the agentic setting, and the threat models they assume. On the defense side, we analyze the prevailing defense strategies, their cost and security trade-offs, and where in the agent lifecycle they are deployed. Finally, we provide a deatiled cross-cutting analysis, where we map which defenses cover which attack classes and chart trends in agent architecture, backbone model usage, and data modality coverage. Taken together, these findings give a researcher a structural understanding of how agentic capabilities, vulnerabilities, and countermeasures relate to one another, and to identify where the field is concentrated and where it is thin.
Sources
- SecVulEval: Benchmarking LLMs for Real-World C/C++ Vulnerability Detection
- Cloud Investigation Automation Framework (CIAF): An AI-Driven Approach to Cloud Forensics
- Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
- KubeIntellect: A Modular LLM-Orchestrated Agent Framework for End-to-End Kubernetes Management
- Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications
- Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
- Demonstrating specification gaming in reasoning models
- RedTeamLLM: an Agentic AI framework for offensive security
- Jailbreaker in Jail: Moving Target Defense for Large Language Models
- AgentGuard: Repurposing Agentic Orchestrator for Safety Evaluation of Tool Orchestration
- Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities
- A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection
- StruQ: Defending Against Prompt Injection with Structured Queries
- Meta-SecAlign: Training LLMs against Prompt Injection for Robust Agents
- ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
- Goal Hijacking Attack on Large Language Models via Pseudo-Conversation Injection
- Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps
- Systems Security Foundations for Agentic Computing
- Securing AI Agents with Information-Flow Control
- Formally Specifying the High-Level Behavior of LLM-Based Agents
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data