From Monoliths to Swarms: A Study of Attack Surface Evolution in the Transition to Multi-Agent Web Systems

arXiv:2608.00202 · cs.CR · Submitted 2026-07-31 · Read on arXiv

Yashaswi Malla, Sandra Siby

cs.CR

Submitted: 2026-07-31

Code: https://github.com/haven-nyuad/webmas

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Multi-Agent System — 13× in this paper · explained in 6 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Verification — 9× in this paper · explained in 2 episodes
• Benchmarking — 8× in this paper · explained in 3 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Ablation — 4× in this paper · explained in 1 episode
• LLM-as-a-Judge — 4× in this paper · explained in 3 episodes
• Large Language Model — 4× in this paper
• AI Agents — 3× in this paper · explained in 2 episodes
• Agentic System — 3× in this paper · explained in 2 episodes
• Attack Success Rate — 3× in this paper
• Denial of Service — 3× in this paper
• Large Language Model (LLM) — 3× in this paper · explained in 3 episodes
• Adversarial Robustness — 2× in this paper · explained in 3 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Multi-Agent Framework — 2× in this paper · explained in 3 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Adversarial scenarios — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Agent Interactions — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Contextual Awareness — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Multi Agent System — 1× in this paper
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Personally Identifiable Information — 1× in this paper
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Single Agent System — 1× in this paper

Sources

• GPT-4V(ision) is a Generalist Web Agent, if Grounded
• Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
• Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
• WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
• SafeArena: Evaluating the Safety of Autonomous Web Agents
• TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
• TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
• Seven Security Challenges in Cross-domain Multi-agent LLM Systems
• Prompt Injection attack against LLM-integrated Applications
• Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems
• The BrowserGym Ecosystem for Web Agent Research
• ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
• AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web
• WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
• Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
• Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
• MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
• WAAA! Web Adversaries Against Agentic Browsers
• MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation
• Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs