Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter3

Model risks

Dangerous agent actions3

Impact

Data and privacy leaks3

System type

AI Agent12coding agent3Multi-agent systems2

Layer

Application layer5

System component

MCP and skills5Memory7Guardrails and judges3Monitors12Reasoning chains3Permissions and sandboxing5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：Multi-agent systemsSystem component：Permissions and sandboxingClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2610.00392

    A2A-TIBA：针对 A2A 协议 LLM 智能体的间接提示注入攻击与三层同构攻防模型

    提出 A2A-TIBA，经 A2A 对等任务间接注入并植入常驻回调

    arXiv
    2610.00392
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    MiniMax-M3, deepseek-v4-pro, glm-5.3 and others8
    AbstractA2A-TIBA 一次植入后绕过智能体，GDA 用四类结果定位防线，ELA-ITL 把信封标注列为第三层。

    A2A-TIBA 把间接提示注入和绕过放进 A2A：gray-box 攻击者已能投递任务，诱导目标部署常驻回调程序后，下令和外传不再经过智能体。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.35557

    论文：容器、权限规则与沙箱都无法区分读取研究代码的是编译器还是编码 Agent

    评测容器、权限规则与沙箱能否区分编译器与编码 Agent 的文件读取

    arXiv
    2609.35557
    Published
    Layer
    Application layer
    Setting
    coding agent
    Abstract此 harness 表达不了编译器可读而智能体不可读，五条路径两边都不覆盖。

    作者在物理流求解器上检查一套编码智能体配置：编译器必须读本组材料与反应模型，这些字节又不得进入模型上下文或离开本机的记录。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2608.07556

    MasDrift：跨多智能体架构的授权保持基准

    提出 MasDrift，评测多智能体在良性任务中的授权保持

    arXiv
    2608.07556
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    DeepSeek V4 Flash, Qwen3.7 Plus, GPT-5.4 Nano and others6
    Abstract授权保持可被测量：层级用未授权动作换完成率，重锚定比沿链携带更稳。

    MasDrift 把多智能体设计中的授权保持做成可测量性质，对象是没有攻击者的普通委托。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2605.14859

    论文提出 AuthBench 基准，评测编码 Agent 能否推断最小权限边界

    提出 AuthBench 评测编码 Agent 最小权限，并验证充足性-紧缩性分解

    arXiv
    2605.14859
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5, GPT-5.3-Codex, GPT-5.4 and others9
    Abstract论文提出权限边界推断基准与两阶段分解方法，有效降低安全暴露。

    本文研究代码智能体在执行终端任务前自主推断最小文件权限边界的能力。

    Paper analysisRead analysis
You have reached the end