Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter4

Attack type

Prompt injection7Poisoning and backdoors5

Impact

Unauthorized actions5

System type

AI Agent8Multi-agent systems3

Attack surface / entry point

User input19Web pages and interfaces8Documents and messages14Tool responses15Tool and skill descriptions5Code repositories and dependencies3Retrieval corpus4Memory writes38Inter-agent messages4Distribution channels3Inference services and hardware0

Layer

Application layer8

System component

MCP and skills57Memory8Guardrails and judges13Monitors11Permissions and sandboxing22
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Inter-agent messagesAttack surface / entry point：Inference services and hardwareSystem component：MemoryClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.02861

    论文提出在 Kubernetes 上保护 AI Agent 的七层纵深防御框架与参考架构

    提出 Kubernetes 运维智能体的七层纵深防御框架与参考架构

    arXiv
    2610.02861
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract把运维智能体当不可信租户，用七层控制在完全攻破假设下约束行动。

    把 Kubernetes 上的运维智能体当作不可信租户，在假定提示注入已完全控制其工具选择的前提下，用基础设施重建数据面与控制面的边界。要解决的是：智能体读日志、注解、工单或 MCP 工具描述时，这些内容可以变成它带着自身凭据执行的命令。模型对齐和分类器只降低概率。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2610.03153

    EvoRiskBench: An evolutionary benchmark for runtime security risks of workspace agents

    构建 EvoRiskBench 评测工作区 Agent 的运行时安全风险

    arXiv
    2610.03153
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Sol, DeepSeek-V4-Pro-0813, Claude Opus 5

    Abstract论文构建了工作空间智能体运行时风险基准 EvoRiskBench，发现高执行力智能体在 IPI 下面临较高安全风险。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.17320

    Emergence World：对长时程多智能体系统开展对抗压力测试

    提出 Emergence World，对长时程多智能体系统开展对抗压力测试

    arXiv
    2609.17320
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Claude Opus 4.8, DeepSeek v4 Pro, Gemini 3.5 Flash and others9

    Abstract作者通过长期平行世界实验指出模型对齐不具备可组合性，单模型群体会产生社会奉承、协同退缩及语言不透明等失效。

    Paper analysisRead analysis
  5. DefensesarXiv 2609.29647

    AgentKernel：面向 Agent 的可信原生操作系统内核

    提出 AgentKernel，用四支柱强制中介 Agent 的输入、工具与记忆

    arXiv
    2609.29647
    Published
    Layer
    Application layer
    Setting
    AI Agent
    AbstractAgentKernel 是四支柱智能体 OS 设计，安全论证未附带实测数字。

    AgentKernel 是把安全做成组织原则的智能体 OS 架构，不是带跑分的攻防评测。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2608.03272

    多智能体协同过滤系统的连接性攻击与防御研究

    复现 AgentCF 上的多智能体攻防并刻画连通性作用

    arXiv
    2608.03272
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
    Abstract连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。

    作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。

    Paper analysisRead analysis
  7. AttacksarXiv 2605.11047

    DeepTrap 框架在 OpenClaw 上自动挖掘智能体执行上下文漏洞

    提出 DEEPTRAP 以搜索可诱导不安全轨迹的执行上下文载荷

    arXiv
    2605.11047
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, GLM-5 and others9
    AbstractDEEPTRAP 用轨迹级搜索发现 OpenClaw 上下文风险，作者称不能只看最终回复。

    DEEPTRAP 是针对 OpenClaw 的自动化红队框架，搜索执行前被改写的文件、记忆、技能、工具元数据或配置，而不是改用户指令。

    Paper analysisRead analysis
  8. AttacksarXiv 2605.08460

    论文建模多智能体网络中的子智能体继承攻击面

    建模并利用多智能体网络中子智能体生成时的记忆继承漏洞

    arXiv
    2605.08460
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    MiniMax M2.5, Llama-4-Maverick-17B-128E-Instruct-FP8, Qwen3.5-Plus and others5
    Abstract形式化子智能体继承，在 OpenClaw 上演示四类编排层漏洞并提出防御。

    作者对多智能体网络里的子智能体继承做形式化分析，并用开源框架上的 PoC 演示编排层如何让单点妥协继续扩散。

    Paper analysisRead analysis
You have reached the end