# sandbox-escape
標記為「sandbox-escape」的 6 篇文章
AI Agent Exploitation
Methodology for exploiting AI agent architectures through confused deputy attacks, goal hijacking, privilege escalation, and sandbox escape.
agentsexploitationtool-useprivilege-escalationsandbox-escape
Code Agent Sandbox Escape Techniques
Develop and test sandbox escape techniques against code execution environments in AI coding assistants.
labssandbox-escapecode-agentsadvanced
Delimiter Escape Attacks
Techniques for escaping delimiters used to separate system and user content in LLM applications, breaking out of sandboxed input regions to inject instructions.
prompt-injectiondelimiter-escapesandbox-escapered-teamingintermediate
AI 代理利用
經混淆代理攻擊、目標劫持、特權升級與沙箱逃逸利用 AI 代理架構之方法論。
agentsexploitationtool-useprivilege-escalationsandbox-escape
Code 代理 Sandbox Escape Techniques
Develop and test sandbox escape techniques against code execution environments in AI coding assistants.
labssandbox-escapecode-agentsadvanced
Delimiter Escape 攻擊s
Techniques for escaping delimiters used to separate system and user content in LLM applications, breaking out of sandboxed input regions to inject instructions.
prompt-injectiondelimiter-escapesandbox-escapered-teamingintermediate