# Can Indirect Prompt Injection Attacks Be Detected and Removed?

arXiv: https://arxiv.org/abs/2502.16580 · HTML: https://mlsanity.com/paper/2502.16580/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 23 Feb 2025.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents](https://mlsanity.com/paper/2406.05870/) (2024)
- [Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?](https://mlsanity.com/paper/2403.06833/) (2024)
- [UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs](https://mlsanity.com/paper/2402.13630/) (2024)
- [Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection](https://mlsanity.com/paper/2308.10819/) (2023)
- [Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications](https://mlsanity.com/paper/2401.07612/) (2024)
- [Defense Against Prompt Injection Attack by Leveraging Attack Techniques](https://mlsanity.com/paper/2411.00459/) (2024)
- [KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection](https://mlsanity.com/paper/2403.02253/) (2024)
- [Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?](https://mlsanity.com/paper/2502.12206/) (2025)
- [Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering](https://mlsanity.com/paper/2410.08085/) (2024)
- [ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty](https://mlsanity.com/paper/2412.20251/) (2024)

## Built on by (most cited first, 30 of 52)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents](https://mlsanity.com/paper/2508.15310/) (2025)
- [Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections](https://mlsanity.com/paper/2602.15654/) (2026)
- [AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection](https://mlsanity.com/paper/2508.01249/) (2025)
- [EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems](https://mlsanity.com/paper/2510.13220/) (2025)
- [MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol](https://mlsanity.com/paper/2505.14590/) (2025)
- [Defending against Indirect Prompt Injection by Instruction Detection](https://mlsanity.com/paper/2505.06311/) (2025)
- [The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis](https://mlsanity.com/paper/2602.10453/) (2026)
- [PromptLocate: Localizing Prompt Injection Attacks](https://mlsanity.com/paper/2510.12252/) (2025)
- [Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges](https://mlsanity.com/paper/2510.23883/) (2025)
- [ASIDE: Architectural Separation of Instructions and Data in Language Models](https://mlsanity.com/paper/2503.10566/) (2025)
- [TopicAttack: An Indirect Prompt Injection Attack via Topic Transition](https://mlsanity.com/paper/2507.13686/) (2025)
- [VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit](https://mlsanity.com/paper/2601.05755/) (2026)
- [Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction](https://mlsanity.com/paper/2504.20472/) (2025)
- [A Framework for Formalizing LLM Agent Security](https://mlsanity.com/paper/2603.19469/) (2026)
- [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://mlsanity.com/paper/2507.17131/) (2025)
- [CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization](https://mlsanity.com/paper/2510.08829/) (2025)
- [WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents](https://mlsanity.com/paper/2602.03792/) (2026)
- [AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management](https://mlsanity.com/paper/2602.07398/) (2026)
- [EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks](https://mlsanity.com/paper/2505.14289/) (2025)
- [Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks](https://mlsanity.com/paper/2511.15203/) (2025)
- [Defense Against Indirect Prompt Injection via Tool Result Parsing](https://mlsanity.com/paper/2601.04795/) (2026)
- [Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning](https://mlsanity.com/paper/2505.14585/) (2025)
- [EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning](https://mlsanity.com/paper/2601.22964/) (2026)
- [ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior](https://mlsanity.com/paper/2512.05745/) (2025)
- [From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs](https://mlsanity.com/paper/2505.14368/) (2025)
- [AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks](https://mlsanity.com/paper/2602.13597/) (2026)
- [Evaluating Privilege Usage of Agents with Real-World Tools](https://mlsanity.com/paper/2603.28166/) (2026)
- [Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods](https://mlsanity.com/paper/2510.03705/) (2025)

## Abstract (arXiv)

Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and inability to distinguish between the original input instructions and maliciously injected instructions. To defend against such attacks, recent studies have developed various detection mechanisms. If we restrict ourselves specifically to works which perform detection rather than direct defense, most of them focus on direct prompt injection attacks, while there are few works for the indirect scenario, where injected instructions are indirectly from external tools, such as a search engine. Moreover, current works mainly investigate injection detection methods and pay less attention to the post-processing method that aims to mitigate the injection after detection. In this paper, we investigate the feasibility of detecting and removing indirect prompt injection attacks, and we construct a benchmark dataset for evaluation. For detection, we assess the performance of existing LLMs and open-source detection models, and we further train detection models using our crafted training datasets. For removal, we evaluate two intuitive methods: (1) the segmentation removal method, which segments the injected document and removes parts containing injected instructions, and (2) the extraction removal method, which trains an extraction model to identify and remove injected instructions.