Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack type

Prompt injection5Poisoning and backdoors3

System type

AI Agent3

Attack surface / entry point

User input13Web pages and interfaces8Documents and messages12Tool responses11Tool and skill descriptions3Code repositories and dependencies3Retrieval corpus4Memory writes30Distribution channels3

Layer

Application layer3

System component

MCP and skills33Memory3Guardrails and judges5Monitors4Permissions and sandboxing6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack type：Poisoning and backdoorsAttack surface / entry point：Tool and skill descriptionsSystem component：MemoryClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.02861

    论文提出在 Kubernetes 上保护 AI Agent 的七层纵深防御框架与参考架构

    提出 Kubernetes 运维智能体的七层纵深防御框架与参考架构

    arXiv
    2610.02861
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract把运维智能体当不可信租户，用七层控制在完全攻破假设下约束行动。

    把 Kubernetes 上的运维智能体当作不可信租户，在假定提示注入已完全控制其工具选择的前提下，用基础设施重建数据面与控制面的边界。要解决的是：智能体读日志、注解、工单或 MCP 工具描述时，这些内容可以变成它带着自身凭据执行的命令。模型对齐和分类器只降低概率。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.29647

    AgentKernel：面向 Agent 的可信原生操作系统内核

    提出 AgentKernel，用四支柱强制中介 Agent 的输入、工具与记忆

    arXiv
    2609.29647
    Published
    Layer
    Application layer
    Setting
    AI Agent
    AbstractAgentKernel 是四支柱智能体 OS 设计，安全论证未附带实测数字。

    AgentKernel 是把安全做成组织原则的智能体 OS 架构，不是带跑分的攻防评测。

    Paper analysisRead analysis
You have reached the end