1
Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer
揭秘本地LLM智能体的安全黑洞，源码审计显示其运行时层可被恶意利用，AI助手并非绝对可靠。
arXiv:2606.21071v1 Announce Type: cross Abstract: Local LLM agents such as OpenClaw and Nanobot run on end-user machines and act on host resources - t…