Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 1 paper
Filter2

Attack type

Jailbreaks1Prompt injection17Poisoning and backdoors9

System component

MCP and skills1Permissions and sandboxing5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：JailbreaksSystem component：MCP and skillsTopic: Agent safetyClear all
  1. DefensesarXiv 2609.28693

    skilder：以角色化技能包为工具型 LLM 智能体做访问控制

    提出 Skilder，按角色渐进下发企业工具并确定性拦截越权调用

    arXiv
    2609.28693
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude Haiku 4.5, Qwen 3.5 122B, Gemma 4 31B and others6
    AbstractSkilder 用单 MCP 服务器按角色交付工具并硬拦截。

    Skilder 把企业工具型智能体的能力按角色打包，经一个 MCP 服务器做渐进发现，使工具范围由服务器而不是提示词来执行。

    Paper analysisRead analysis
You have reached the end