Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter4

Attack type

Prompt injection5

Defense type

Inference-time intervention0Detection and filtering3Instruction–data separation6Permissions and approval3

Impact

Unauthorized actions4

System type

Models and APIs84LLM applications28AI Agent116coding agent19science agent5web agent6Browser and computer use4Multi-agent systems13Embodied systems and robotics3

Attack surface / entry point

Web pages and interfaces4

Layer

Application layer6

System component

Guardrails and judges3Permissions and sandboxing3
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.
Defense type：Inference-time interventionDefense type：Detection and filteringDefense type：Permissions and approvalSystem type：web agentClear 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
  6. Evaluation and benchmarksarXiv 2510.01354

    WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    arXiv
    2510.01354
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end