# tool-exploitation
標記為「tool-exploitation」的 4 篇文章
Agentic Exploitation
Comprehensive coverage of security vulnerabilities in agentic AI systems, including MCP tool exploitation, multi-agent protocol attacks, function calling abuse, memory system compromise, framework-specific weaknesses, and workflow pattern attacks.
agenticagentsmcpfunction-callingmulti-agenta2atool-exploitation
MCP & Tool Surface Exploitation
Attack methodology for the Model Context Protocol (MCP) covering tool schema manipulation, tool poisoning, resource URI traversal, cross-server pivoting, and sampling API abuse.
mcptool-exploitationprotocol-securitytool-poisoningsampling-api
代理式利用
代理式 AI 系統中安全漏洞的完整涵蓋，包含 MCP 工具利用、多代理協議攻擊、函式呼叫濫用、記憶體系統入侵、框架特定弱點與工作流程模式攻擊。
agenticagentsmcpfunction-callingmulti-agenta2atool-exploitation
MCP & 工具 Surface 利用ation
攻擊 methodology for the 模型 Context Protocol (MCP) covering tool schema manipulation, tool poisoning, resource URI traversal, cross-server pivoting, and sampling API abuse.
mcptool-exploitationprotocol-securitytool-poisoningsampling-api