Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter5

Attack type

Prompt injection4

Defense type

Instruction–data separation3Permissions and approval3

Impact

Unauthorized actions3

System type

Models and APIs31LLM applications4AI Agent102coding agent14science agent4web agent4Multi-agent systems13

Attack surface / entry point

Web pages and interfaces3

Layer

Model layer0Application layer4

System component

RAG3Guardrails and judges4Reasoning chains1Permissions and sandboxing3Vision7Multimodal7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
System type：web agentLayer：Model layerLayer：Application layerSystem component：Reasoning chainsSystem component：Permissions and sandboxingClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2608.24017

    WebMCP-Phalanx：为浏览器内 LLM Agent 工具调用建立信任边界

    提出 WebMCP-Phalanx，用能力凭证与双智能体隔离浏览器工具调用

    arXiv
    2608.24017
    Published
    Layer
    Application layer
    Setting
    web agent
    AbstractPhalanx 用浏览器凭证绑定工具所有权，Q/P 分离拦住描述注入，工具名与返回值仍有残留。

    WebMCP-Phalanx针对浏览器里的 WebMCP 智能体：在 SOP 下补工具所有权，并把语义检查从有工具权的执行中分开。

    Paper analysisRead analysis
  4. AttacksarXiv 2406.12814

    论文提出 ARE 框架，在 VisualWebArena 上评估多模态 Agent 的对抗鲁棒性

    提出 ARE 框架与图像文本攻击，评测多模态网页 Agent 的对抗鲁棒性

    arXiv
    2406.12814
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, GPT-4V, Claude-3-Opus and others4

    Abstract系统评估多模态网页智能体的脆弱性，指出推理时计算组件被攻破会加剧系统风险。

    Paper analysisRead analysis
You have reached the end