Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter5

Defense type

Detection and filtering4Instruction–data separation0Permissions and approval1Monitoring and auditing2

System type

AI Agent9coding agent2

Attack surface / entry point

User input3Tool responses3Tool and skill descriptions5Distribution channels2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationDefense type：Permissions and approvalDefense type：Monitoring and auditingSystem type：coding agentAttack surface / entry point：Distribution channelsClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2608.21101

    ClawSentry：面向自主 LLM Agent 的渐进式多层安全监控网关

    提出 ClawSentry 多层监控网关，在技能准入和运行时拦截恶意技能与隐藏指令

    arXiv
    2608.21101
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Codex/GPT-5.4, Codex/GPT-5.5, Claude Code/GLM-5.1 and others6
    AbstractClawSentry 用包准入、三级运行时门控和反绕过，压低 skill 攻击并保住干净任务。

    ClawSentry 是挂在智能体运行时之外的安全监督网关，用来同时盖住 skill 执行的多个生命周期边界，并把已被拒绝的效果记到会话里。

    Paper analysisRead analysis
  2. DefensesarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。

    Paper analysisRead analysis
You have reached the end