# tool-poisoning
標記為「tool-poisoning」的 7 篇文章
MCP 與工具面利用
Model Context Protocol（MCP）的攻擊方法論，涵蓋工具 schema 操弄、工具投毒、資源 URI 穿越、跨伺服器轉跳，以及取樣 API 濫用。
mcptool-exploitationprotocol-securitytool-poisoningsampling-api
案例研究:MCP 早期漏洞揭露
分析早期 MCP 漏洞揭露,包含 Invariant Labs 的工具投毒研究。
case-studiesmcpvulnerabilitiestool-poisoning
案例研究:MCP 工具投毒
針對 Model Context Protocol(MCP)伺服器的工具投毒攻擊分析,與生態系的信任模型挑戰。
case-studiesmcptool-poisoninginvariant-labsagent-securityprompt-injection
MCP 工具 投毒 攻擊
利用 MCP tool descriptions to inject instructions that redirect agent behavior.
labsmcptool-poisoningintermediate
實驗室: 工具 Result 投毒
動手實驗室,主題為poisoning tool outputs,以重新導向 agent behavior by injecting malicious content through tool results.
labtool-poisoningagentsindirect-injectionagentic-attacks
MCP Tool Poisoning 攻擊 詳解
Walkthrough of exploiting MCP tool descriptions to redirect agent behavior via hidden instructions.
walkthroughsmcptool-poisoningagent
MCP 工具 Shadowing
進階 walkthrough of creating shadow tools that override legitimate MCP (模型 Context Protocol) tools, enabling interception and manipulation of agent-tool interactions.
mcptool-shadowingmodel-context-protocolagent-securitytool-poisoningwalkthrough