Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Defense type

Detection and filtering5Instruction–data separation2Permissions and approval2Monitoring and auditing4Watermarking and provenance7

System type

Models and APIs0LLM applications3AI Agent25coding agent3

Attack surface / entry point

User input8Documents and messages0Tool and skill descriptions3

Layer

Application layer3

System component

MCP and skills3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationDefense type：Permissions and approvalSystem type：Models and APIsSystem type：coding agentAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool and skill descriptionsClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
  3. 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
You have reached the end