Cover Image

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Litvak, Ron
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

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
by: Liu, Zesen, et al.
Published: (2025)

Securing AI Agents Against Prompt Injection Attacks
by: Ramakrishnan, Badrinath, et al.
Published: (2025)

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
by: Li, Xueyi, et al.
Published: (2026)

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

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)

A Comprehensive Study of Exploitable Patterns in Smart Contracts: From Vulnerability to Defense
by: Ding, Yuchen, et al.
Published: (2025)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
by: Evtimov, Ivan, et al.
Published: (2025)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
by: Xiang, Chong, et al.
Published: (2026)

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
by: Sehwag, Udari Madhushani, et al.
Published: (2026)

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

Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack
by: Yue, Murong, et al.
Published: (2025)

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
by: Chen, Sizhe, et al.
Published: (2025)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
by: Zhang, Hanrong, et al.
Published: (2024)

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems
by: Balashov, Andrii, et al.
Published: (2025)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
by: Ning, Liang-bo, et al.
Published: (2025)

Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms
by: Gasmi, Tarek, et al.
Published: (2025)

A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares
by: Cohen, Stav, et al.
Published: (2024)

Joint Optimization of Prompt Security and System Performance in Edge-Cloud LLM Systems
by: Huang, Haiyang, et al.
Published: (2025)

Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents
by: Puppala, Sai, et al.
Published: (2026)

Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models
by: Nakka, Kalyan, et al.
Published: (2024)

Security of Internet of Agents: Attacks and Countermeasures
by: Wang, Yuntao, et al.
Published: (2025)

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

Agent Audit: A Security Analysis System for LLM Agent Applications
by: Zhang, Haiyue, et al.
Published: (2026)

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
by: Wang, Zhun, et al.
Published: (2026)

Defenses Against Prompt Attacks Learn Surface Heuristics
by: Li, Shawn, et al.
Published: (2026)

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
by: Johnson, Sam, et al.
Published: (2025)

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
by: Zhang, Dongsen, et al.
Published: (2025)

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
by: Zhang, Zhixiang, et al.
Published: (2026)

Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack
by: Kang, Daewon, et al.
Published: (2025)

LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures
by: Aguilera-Martínez, Francisco, et al.
Published: (2025)

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
by: Arzanipour, Atousa, et al.
Published: (2025)

Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts
by: Zhang, Xing, et al.
Published: (2026)

SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection
by: Hasan, Touseef, et al.
Published: (2026)

Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
by: Xing, Wenpeng, et al.
Published: (2025)

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
by: Nie, Yuzhou, et al.
Published: (2025)

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair
by: Gajjar, Jugal, et al.
Published: (2025)

Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models
by: Del Rosario, Ron F.
Published: (2025)

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
by: Zhao, Wei, et al.
Published: (2026)

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

LProtector: An LLM-driven Vulnerability Detection System
by: Sheng, Ze, et al.
Published: (2024)