Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer

Abstract

Local LLM agents such as OpenClaw and Nanobot run on end-user machines and act on host resources - the shell, filesystem, browser, stored credentials, and messaging applications - through natural-language goals. These agents have become privileged software runtimes that mediate between user intent, model outputs, and host-level actions. Existing research characterizes the landscape through prompt injection, malicious skills, marketplace risks, or black-box evaluation of agents. But the implement

Categories

Framework mappings

Suggested from the entry's categories.

@misc{zhang2026local,
  title = {{Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer}},
  author = {Zhengsong Zhang and Zongze Li and Jiawei Guo and Haipeng Cai},
  year = {2026},
  month = jun,
  eprint = {2606.21071},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.21071}
}