Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Attack type

Prompt injection4

Impact

Harmful content3Unauthorized actions28Data and privacy leaks6Output manipulation11Availability and reliability16

System type

Models and APIs64LLM applications15AI Agent54coding agent15web agent6Multi-agent systems7Embodied systems and robotics0

Attack surface / entry point

Web pages and interfaces3

Layer

Application layer6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Impact：Data and privacy leaksSystem type：web agentSystem type：Embodied systems and roboticsClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2610.05586

    AgentDoxx：联网搜索 Agent 对匿名访谈文本的再识别评测

    构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别

    arXiv
    2610.05586
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.6 Terra, GPT-5 Mini, GPT-4.1 Mini and others10

    Abstract论文提出了已知身份的重识别基准 AGENTDOXX，揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.32915

    AgentTell：浏览器 Agent 的行为侧信道泄漏基准

    构建 AGENTTELL 基准，测量浏览器 Agent 的行为侧信道隐私泄露

    arXiv
    2609.32915
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    Claude Sonnet 5, Gemini 3.7 Flash, GPT-5.6 Luna and others6

    Abstract论文评估了浏览器智能体的行为侧信道泄露风险，并基于近万次会话提供了评测数据。

    Paper analysisRead analysis
  4. 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
  5. AttacksarXiv 2608.04741

    LoginTrap：针对 LLM Web Agent 的任务无关钓鱼式间接提示注入攻击

    提出 LoginTrap，以网页弹窗诱导 Web Agent 提交敏感信息

    arXiv
    2608.04741
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Gemini 3 Flash, Claude Sonnet 4 and others7

    Abstract揭示网络智能体在黑盒网页下的登录诱导风险，利用模糊测试生成话术并跨骨干和架构验证了隐私泄露威胁。

    Paper analysisRead analysis
  6. AttacksarXiv 2605.05509

    研究者提出面向 Agent 浏览器的 Web 威胁模型，梳理 20 类攻击并在 4 个模型上复现

    提出面向智能体浏览器的 Web 威胁模型并复现混淆攻击

    arXiv
    2605.05509
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5, Claude-Sonnet-4.6, Kimi-k2p5 and others8
    Abstract作者提出面向智能体浏览器的 Web 威胁模型与攻击分类，测试显示传统混淆攻击可复现且能绕过现有防御。

    这篇论文研究了智能体浏览器在面临传统 Web 攻击者时的安全性问题，指出当前针对提示词注入的安全假设无法抵御基于正常 Web 交互模式的混淆攻击。

    Paper analysisRead analysis
You have reached the end