Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Attack technique

Automated search1

Attack surface / entry point

Documents and messages3Tool and skill descriptions1Memory writes4

System component

MCP and skills16Memory1Guardrails and judges5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack technique：Automated searchAttack surface / entry point：Tool and skill descriptionsSystem component：MemoryClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2605.11047

    DeepTrap 框架在 OpenClaw 上自动挖掘智能体执行上下文漏洞

    提出 DEEPTRAP 以搜索可诱导不安全轨迹的执行上下文载荷

    arXiv
    2605.11047
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, GLM-5 and others9
    AbstractDEEPTRAP 用轨迹级搜索发现 OpenClaw 上下文风险，作者称不能只看最终回复。

    DEEPTRAP 是针对 OpenClaw 的自动化红队框架，搜索执行前被改写的文件、记忆、技能、工具元数据或配置，而不是改用户指令。

    Paper analysisRead analysis
You have reached the end