No article text was recorded for this version.
indirect prompt injection
Version 1 of 1255 papers412 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Takedown: How It's Done in Modern Coding Agent Exploits
- Blog: WIPI: A New Web Threat for LLM-Driven Web Agents
- Blog: Emerging Cyber Attack Risks of Medical AI Agents
- Blog: On the Security of Tool-Invocation Prompts for LLM-Based Agentic Systems: An Empirical Risk Assessment
- Blog: WAAA! Web Adversaries Against Agentic Browsers
- Blog: LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
- Blog: Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
- Blog: MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control
- Blog: SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime
- Blog: InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
- Blog: AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways
- Blog: Lateral Data Exfiltration in MCP: How One Compromised Server Captures Cross-Domain Agent Data
- Blog: InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
- Blog: LLM-Based Agents for Tool Learning: A Survey
- Blog: Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
- Blog: Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
- Blog: QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
- Blog: BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
- Blog: Securing AI Agents with Information-Flow Control
- Blog: OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use
- Blog: A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
- Blog: EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
- Blog: Web Agents Leak Sensitive Data on Simple Scalable Websites
- Blog: Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
- Blog: "Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
- Blog: Tool Learning with Large Language Models: A Survey
- Blog: Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
- Blog: The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration
- Blog: RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
- Blog: MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
- Blog: Safety at Scale: A Comprehensive Survey of Large Model Safety
- Blog: Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
- Blog: Countering Autonomous Cyber Threats
- Blog: Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
- Blog: BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
- Blog: Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks
- Blog: Unveiling Privacy Risks in LLM Agent Memory
- Blog: Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
- Blog: MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
- Blog: A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
- Blog: Whispers in the Machine: Confidentiality in LLM-integrated Systems
- Blog: Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
- Blog: Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
- Blog: System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
- Blog: Unleashing Cheapfakes through Trojan Plugins of Large Language Models
- Blog: A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models
- Blog: MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
- Blog: A Systematization of Security Vulnerabilities in Computer Use Agents
- Blog: From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
- Blog: Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks
- Blog: ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
- Blog: EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
- Blog: MELON: Indirect Prompt Injection Defense via Masked Re-execution and Tool Comparison
- Blog: Exploiting Novel GPT-4 APIs
- Blog: SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
- Blog: Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
- Blog: Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
- Blog: Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems
- Blog: More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
- Blog: Progent: Programmable Privilege Control for LLM Agents
Showing 60 of 255 papers.
History & citation
Current · Permanent link
- Indirect Prompt Injection in LLM Agents merged into this direction (74% overlap)
- Defending Autonomous Agents from Environmental Instruction Hijacking merged into this direction (79% overlap)
- Execution-Centric Defense Against Indirect Prompt Injection merged into this direction (63% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_indirect_prompt_injection_224a59a6,
title = {indirect prompt injection},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/indirect-prompt-injection/rdr_224a59a6ce83452eb5dee77588d0cbab},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_indirect_prompt_injection_224a59a6_v1,
title = {indirect prompt injection},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/indirect-prompt-injection/rdr_224a59a6ce83452eb5dee77588d0cbab/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}