Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter4

Attack type

Prompt injection3

Defense type

Detection and filtering3

Impact

Unauthorized actions3

System type

LLM applications36AI Agent119coding agent16science agent4web agent5Multi-agent systems15

Attack surface / entry point

Web pages and interfaces3

Layer

Application layer5

System component

Memory1RAG3Guardrails and judges4Permissions and sandboxing3Vision7Multimodal7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
System type：web agentLayer：Application layerSystem component：MemorySystem component：Guardrails and judgesClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2604.06240

    研究者开源 Universal Verifier 与 CUAVerifierBench，用于验证计算机使用 Agent 轨迹

    构建 Universal Verifier 核验计算机使用 Agent 轨迹

    arXiv
    2604.06240
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.2, GPT-4o, o4-mini and others8
    Abstract四条设计原则叠成 Universal Verifier，作者称其与人类一致程度相当且假阳性近零。

    Universal Verifier 给计算机使用轨迹打过程分和结果分，并定位失败。CUAVerifierBench 用人工标签衡量这种验证器。

    Paper analysisRead analysis
  2. AttacksarXiv 2604.02623

    论文提出 eTAMP 攻击：网页内容注入可跨会话污染 Web Agent 记忆

    提出 eTAMP，用网页内容跨会话投毒 Web Agent 轨迹记忆并诱导越权操作

    arXiv
    2604.02623
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5-mini, GPT-5.2, GPT-OSS-120B and others6
    Abstract论文提出了基于环境注入的跨任务记忆投毒攻击 eTAMP，作者报告智能体在环境压力下易感性增加且能力与安全并不协同。

    该论文评估了基于大语言模型的 Web 智能体在利用历史交互轨迹进行记忆增强时的安全脆弱性。

    Paper analysisRead analysis
  5. 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