Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Abstract

Autonomous Large Language Model (LLM) agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorized tool execution. Securing these systems requires effective information flow tracking. Yet, traditional taint analysis that is designed for program memory states fundamentally fails when applied to LLM

Categories

Framework mappings

Suggested from the entry's categories.

@misc{cai2026ghost,
  title = {{Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents}},
  author = {Yuandao Cai and Wensheng Tang and Cheng Wen and Shengchao Qin},
  year = {2026},
  month = apr,
  eprint = {2604.23374},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.23374}
}