WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents

arXiv:2608.24017 · cs.CR, cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

Comments: 8 pages, 1 figure, AAAI2027

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

Terminology

• Provenance — 8× in this paper · explained in 4 episodes
• Verification — 4× in this paper · explained in 2 episodes
• AI Agents — 3× in this paper · explained in 2 episodes
• Decoupling — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Same-Origin Policy — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adversarial Model — 1× in this paper · explained in 1 episode
• Agentic Evaluation — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Introspection — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Task Planning — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
• MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
• ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
• ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
• Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
• ToolTweak: An Attack on Tool Selection in LLM-based Agents
• Les Dissonances: Cross-Tool Harvesting and Polluting in Pool-of-Tools Empowered LLM Agents
• AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
• MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
• IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems
• ACE: A Security Architecture for LLM-Integrated App Systems
• Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
• Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents

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