# The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis

arXiv: https://arxiv.org/abs/2602.10453 · HTML: https://mlsanity.com/paper/2602.10453/

## Key facts

- Cited by 30 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 67 of its 96 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

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

## Builds on (most cited first, 30 of 67)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents](https://mlsanity.com/paper/2503.00061/) (2025)
- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [Automatic and Universal Prompt Injection Attacks against Large Language Models](https://mlsanity.com/paper/2403.04957/) (2024)
- [PromptArmor: Simple yet Effective Prompt Injection Defenses](https://mlsanity.com/paper/2507.15219/) (2025)
- [System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective](https://mlsanity.com/paper/2409.19091/) (2024)
- [AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection](https://mlsanity.com/paper/2502.11448/) (2025)
- [Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents](https://mlsanity.com/paper/2503.15547/) (2025)
- [MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents](https://mlsanity.com/paper/2502.05174/) (2025)
- [RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage](https://mlsanity.com/paper/2502.08966/) (2025)
- [Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications](https://mlsanity.com/paper/2403.02817/) (2024)
- [ACE: A Security Architecture for LLM-Integrated App Systems](https://mlsanity.com/paper/2504.20984/) (2025)
- [Can Indirect Prompt Injection Attacks Be Detected and Removed?](https://mlsanity.com/paper/2502.16580/) (2025)
- [AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection](https://mlsanity.com/paper/2508.01249/) (2025)
- [Adversarial Search Engine Optimization for Large Language Models](https://mlsanity.com/paper/2406.18382/) (2024)
- [RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection](https://mlsanity.com/paper/2510.04885/) (2025)
- [Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAI](https://mlsanity.com/paper/2411.18241/) (2024)
- [Defending Against Prompt Injection With a Few DefensiveTokens](https://mlsanity.com/paper/2507.07974/) (2025)
- [Defending against Indirect Prompt Injection by Instruction Detection](https://mlsanity.com/paper/2505.06311/) (2025)
- [PromptLocate: Localizing Prompt Injection Attacks](https://mlsanity.com/paper/2510.12252/) (2025)
- [HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2410.22832/) (2024)
- [Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution](https://mlsanity.com/paper/2506.01055/) (2025)
- [SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems](https://mlsanity.com/paper/2506.07564/) (2025)

## Built on by (most cited first, 30 of 30)

- [Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents](https://mlsanity.com/paper/2605.26497/) (2026)
- [ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection](https://mlsanity.com/paper/2605.03378/) (2026)
- [The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck](https://mlsanity.com/paper/2605.11039/) (2026)
- [Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks](https://mlsanity.com/paper/2603.30016/) (2026)
- [Reframing LLM Agent Security as an Agent-Human Interaction Problem](https://mlsanity.com/paper/2605.24309/) (2026)
- [SkillGuard: A Permission-Centric Framework for Agent Skill Security](https://mlsanity.com/paper/2606.03024/) (2026)
- [AI Agents Under EU Law](https://mlsanity.com/paper/2604.04604/) (2026)
- [No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills](https://mlsanity.com/paper/2605.13044/) (2026)
- [Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens](https://mlsanity.com/paper/2606.30755/) (2026)
- [The Moltbook Observatory Archive: an incremental dataset of agent-only social network activity](https://mlsanity.com/paper/2605.13860/) (2026)
- [Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing](https://mlsanity.com/paper/2607.18485/) (2026)
- [AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations](https://mlsanity.com/paper/2606.02240/) (2026)
- [Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents](https://mlsanity.com/paper/2606.13385/) (2026)
- [AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories](https://mlsanity.com/paper/2609.06972/) (2026)
- [Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation](https://mlsanity.com/paper/2605.06393/) (2026)
- [AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection](https://mlsanity.com/paper/2608.04053/) (2026)
- [LongPIBench: A Long-Context Benchmark for Prompt Injection](https://mlsanity.com/paper/2608.28411/) (2026)
- [A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development](https://mlsanity.com/paper/2606.14816/) (2026)
- [Agent Security Meets Regulatory Reality -- A Practitioner Systematization of Autonomous-Agent Threats and Controls in Regulated Financial Systems](https://mlsanity.com/paper/2606.29142/) (2026)
- [Just Testing, Move Along: Evasion of LLM-based System Log Interpretation by Prompt Injection](https://mlsanity.com/paper/2607.24174/) (2026)
- [Distributing Security Controls Through Harness Engineering](https://mlsanity.com/paper/2607.25890/) (2026)
- [Workspace Topology as an Attack Vector in Agentic Coding Assistants](https://mlsanity.com/paper/2608.14876/) (2026)
- [Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation](https://mlsanity.com/paper/2608.18034/) (2026)
- [DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents](https://mlsanity.com/paper/2609.10892/) (2026)
- [Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems](https://mlsanity.com/paper/2609.22949/) (2026)
- [Attack Success Rate Is Not a Number: On Measurement Validity in Agentic AI Security Evaluation](https://mlsanity.com/paper/2609.25173/) (2026)
- [Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents](https://mlsanity.com/paper/2609.28585/) (2026)
- [Pincer: Resource Authorization for Agents using a Digital Twin](https://mlsanity.com/paper/2610.02569/) (2026)
- [RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents](https://mlsanity.com/paper/2610.06401/) (2026)
- [Prompt-Injection Probes Learn the Conversation, Not Just the Injection](https://mlsanity.com/paper/2610.18408/) (2026)

## Abstract (arXiv)

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK presents a comprehensive overview of the PI landscape, covering attacks, defenses, and their evaluation practices. Through a systematic literature review and quantitative analysis, we establish taxonomies that categorize PI attacks by payload generation strategies (heuristic vs. optimization) and defenses by intervention stages (text, model, and execution levels). Our analysis reveals a key limitation shared by many existing defenses and benchmarks: they largely overlook context-dependent tasks, in which agents are authorized to rely on runtime environmental observations to determine actions. To address this gap, we introduce AgentPI, a new benchmark designed to systematically evaluate agent behavior under context-dependent interaction settings. Using AgentPI, we empirically evaluate representative defenses and show that no single approach can simultaneously achieve high trustworthiness, high utility, and low latency. Moreover, we show that many defenses appear effective under existing benchmarks by suppressing contextual inputs, yet fail to generalize to realistic agent settings where context-dependent reasoning is essential. This SoK distills key takeaways and open research problems, offering structured guidance for future research and practical deployment of secure LLM agents.