Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter5

Attack type

Prompt injection6Poisoning and backdoors4

Impact

Unauthorized actions5

System type

AI Agent6coding agent2

Attack surface / entry point

User input19Web pages and interfaces17Documents and messages17Tool responses17Tool and skill descriptions6Code repositories and dependencies3Retrieval corpus4Memory writes36Inter-agent messages4Images, audio and video17Distribution channels4

Layer

Application layer6

System component

MCP and skills53Memory5Guardrails and judges10Monitors7Permissions and sandboxing16Vision1
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：AI AgentSystem type：coding agentAttack surface / entry point：Tool and skill descriptionsSystem component：MemorySystem component：VisionClear all

Another 254papers 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 2609.35912

    MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

    提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作

    arXiv
    2609.35912
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6

    Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。

    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. 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
You have reached the end