Cover Image

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sehwag, Udari Madhushani, Shan, Zhengyang, Liu, Heming, Lakshan, Dileepa, Brandifino, Joseph, Fenkell, Max
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can LLMs be Scammed? A Baseline Measurement Study
by: Sehwag, Udari Madhushani, et al.
Published: (2024)

AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
by: Karthikeyan, Harish, et al.
Published: (2025)

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
by: Lee, Michael S., et al.
Published: (2026)

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection
by: Shan, Zhengyang, et al.
Published: (2026)

The Vulnerability of LLM Rankers to Prompt Injection Attacks
by: Yin, Yu, et al.
Published: (2026)

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
by: Campbell, David, et al.
Published: (2026)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
by: Ying, Zonghao, et al.
Published: (2026)

Prompt Injection Attack to Tool Selection in LLM Agents
by: Shi, Jiawen, et al.
Published: (2025)

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
by: Wang, Reachal, et al.
Published: (2025)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
by: Wang, Zhilong, et al.
Published: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
by: Qi, Senmao, et al.
Published: (2025)

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
by: Wang, Yihan, et al.
Published: (2025)

LiteShield: Hybrid Feature Selection-Driven Lightweight Intrusion Detection for Resource-Constrained IoT Networks
by: Mabulage, Dileepa, et al.
Published: (2026)

DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection
by: Ren, Junyu, et al.
Published: (2026)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
by: Maloyan, Narek, et al.
Published: (2026)

PINA: Prompt Injection Attack against Navigation Agents
by: Liu, Jiani, et al.
Published: (2026)

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
by: Weng, Shihao, et al.
Published: (2026)

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
by: He, Yu, et al.
Published: (2026)

Design Patterns for Securing LLM Agents against Prompt Injections
by: Beurer-Kellner, Luca, et al.
Published: (2025)

LogJack: Indirect Prompt Injection Through Cloud Logs Against LLM Debugging Agents
by: Shah, Harsh
Published: (2026)

Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
by: Wei, Boyi, et al.
Published: (2025)

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
by: Zhong, Peter Yong, et al.
Published: (2025)

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
by: Wang, Peiran, et al.
Published: (2026)

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
by: Lee, Donghyun, et al.
Published: (2024)

Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy
by: Gudiño-Rosero, Jairo, et al.
Published: (2025)

AgentWatcher: A Rule-based Prompt Injection Monitor
by: Wang, Yanting, et al.
Published: (2026)

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures
by: Benjamin, Victoria, et al.
Published: (2024)

From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?
by: Pedro, Rodrigo, et al.
Published: (2023)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
by: Hossain, S M Asif, et al.
Published: (2025)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
by: Debenedetti, Edoardo, et al.
Published: (2024)

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
by: Dziemian, Mateusz, et al.
Published: (2026)

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
by: Li, Fanxiao, et al.
Published: (2026)

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems
by: Maloyan, Narek, et al.
Published: (2026)

AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
by: Wang, Zhun, et al.
Published: (2025)

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
by: Ferrag, Mohamed Amine, et al.
Published: (2025)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
by: Zhan, Qiusi, et al.
Published: (2025)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
by: Chen, Yulin, et al.
Published: (2026)

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems
by: Alam, Md Takrim Ul, et al.
Published: (2026)

When Skills Lie: Hidden-Comment Injection in LLM Agents
by: Wang, Qianli, et al.
Published: (2026)

Optimization-based Prompt Injection Attack to LLM-as-a-Judge
by: Shi, Jiawen, et al.
Published: (2024)