Skip to content

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

Oct 12 · Monday

All papers

Found 10 papers
Filter3

Attack type

Jailbreaks4Prompt injection7

Defense type

Permissions and approval9

Impact

Unauthorized actions10

System type

AI Agent10

Attack surface / entry point

User input10Web pages and interfaces11Documents and messages10Tool responses17Tool and skill descriptions10Code repositories and dependencies3Retrieval corpus4Memory writes5Inter-agent messages3Distribution channels6

Layer

Application layer10

System component

MCP and skills6Memory6Guardrails and judges7Monitors6Permissions and sandboxing10
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Impact：Unauthorized actionsAttack surface / entry point：User inputSystem component：Permissions and sandboxingClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2609.34518

    SEAD 论文提出工具型 Agent 的状态视角攻击与防御方法 DART 与 SAGE

    提出工具型 Agent 的自适应攻击 DART 与预执行防御 SAGE

    arXiv
    2609.34518
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Luna, GPT-5.6 Terra, Gemini 3.8 Flash and others5

    Abstract论文提出状态控制框架 SEAD、攻击 DART 与防御 SAGE，实验显示执行反馈与环境探测在攻防交互中具有关键作用。

    Paper analysisRead analysis
  4. 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
  5. DefensesarXiv 2609.24165

    APEXA 为同步辐射数据处理的 LLM 多智能体加装执行完整性护栏

    提出 APEXA，在工具层拒绝无执行支撑的结果并拦截电机命令

    arXiv
    2609.24165
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    GPT-5-mini, GPT-5.4, Claude Opus 4.7 and others4
    Abstract作者称执行是否发生要由工具层核对，而不能只靠提示词。

    APEXA 是先进光子源上的数据还原框架，用工具层代码约束语言模型智能体的工具调用。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.22573

    研究提出面向企业 MCP 的零信任授权与工具发现方案

    提出企业 MCP 零信任授权与发现扩展，在架构上拒绝提示注入下的越权调用

    arXiv
    2609.22573
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gpt-5, claude-sonnet-4-6, claude-opus-4-7 and others6
    Abstract同一份按工具声明同时管 MCP 的发现、列表和调用，使注入不能扩大已有凭证的权限。

    作者把零信任放在 MCP 工具调用边界：智能体即使被提示注入，也不能调用其凭证范围之外的工具。问题来自三点部署性质。调用意图会随不可信上下文改变。

    Paper analysisRead analysis
You have reached the end