Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 2 papers
Filter2

Attack surface / entry point

User input6Web pages and interfaces4Documents and messages4Tool responses7Tool and skill descriptions14Memory writes2Inter-agent messages3Distribution channels7

System component

MCP and skills2Memory9Permissions and sandboxing7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack surface / entry point：Memory writesSystem component：MCP and skillsTopic: Agent safetyClear all
  1. 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
  2. DefensesarXiv 2603.11619

    驯服 OpenClaw：自主 LLM 智能体威胁的安全分析与缓解

    提出对齐五阶段的纵深防御，缓解自主 Agent 跨阶段威胁

    arXiv
    2603.11619
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract这是对 OpenClaw 的生命周期威胁分析与分层缓解设计，案例为定性证据。

    这是对 OpenClaw 的生命周期威胁分析，并配套一套分层缓解设计。要处理的问题是：自主智能体把即时通讯、持久记忆、第三方插件和高权限执行连在一起之后，攻击不再限于单轮越狱，而会跨初始化到执行的多个阶段复合。作者认为只加固单个接口的防御，挡不住这种跨时间攻击。

    Paper analysisRead analysis
You have reached the end