Skip to content

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

Oct 13 · Tuesday

Agent safety · Papers

Found 1 paper
Filter4

Attack type

Jailbreaks5Prompt injection40Poisoning and backdoors11Extraction and theft1

Defense type

Instruction–data separation1Permissions and approval1Monitoring and auditing0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：Extraction and theftDefense type：Instruction–data separationDefense type：Permissions and approvalDefense type：Monitoring and auditingTopic: Agent safetyClear all
  1. 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
You have reached the end