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

Abstract

The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent execution into a browser security model centered on the Same-Origin Policy (SOP) leaves insufficient provenance and lifecycle guarantees for agent-accessible tools, creating three risks: subject-attribution spoofing, uncontrolled tool lifecycles, and semantic prompt injection. We propose WebMCP-Phalanx, a dual-layer agent runtime architecture. Its

Categories

Framework mappings

Suggested from the entry's categories.

@misc{lee2026webmcpphalanx,
  title = {{WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents}},
  author = {Lin-Fa Lee and YI-YU Chang and Kuo-Hui Yeh},
  year = {2026},
  month = aug,
  eprint = {2608.24017},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.24017}
}