# sandbox
標記為「sandbox」的 8 篇文章
Code Agent Sandbox Escape
Techniques for escaping sandboxed code execution environments in AI code agents.
Sandbox Escape via Injection
Using prompt injection as a vector for escaping application sandboxes and achieving unauthorized code execution or system access.
Sandboxed Tool Execution
Step-by-step walkthrough for running LLM tool calls in isolated sandboxes, covering container-based isolation, resource limits, network restrictions, and output sanitization.
AutoGen Multi-Agent System Testing
End-to-end walkthrough for security testing AutoGen multi-agent systems: agent enumeration, inter-agent injection, code execution sandbox assessment, conversation manipulation, and escalation path analysis.
Code 代理 Sandbox Escape
Techniques for escaping sandboxed code execution environments in AI code agents.
Sandbox Escape via Injection
Using prompt injection as a vector for escaping application sandboxes and achieving unauthorized code execution or system access.
沙箱式工具執行
於隔離沙箱中執行 LLM 工具呼叫的逐步教學，涵蓋以容器為本之隔離、資源限制、網路限制與輸出消毒。
AutoGen Multi-代理 System Testing
End-to-end walkthrough for security testing AutoGen multi-agent systems: agent enumeration, inter-agent injection, code execution sandbox assessment, conversation manipulation, and escalation path analysis.