Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Attack type

Poisoning and backdoors3

Attack technique

Dormant triggers3

Impact

Unauthorized actions4

System type

AI Agent25coding agent3web agent1Multi-agent systems3

Attack surface / entry point

Memory writes3

Layer

Application layer4

System component

MCP and skills14Memory4Guardrails and judges6Monitors5Permissions and sandboxing7Vision6Multimodal6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Impact：Unauthorized actionsSystem type：coding agentSystem type：web agentSystem component：MemoryClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.05241

    StateWise：在 Agent 执行动作前诊断并修复持久操作状态

    提出 StateWise，在编码智能体行动前诊断并修复失效持久状态

    arXiv
    2610.05241
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, DeepSeek v4 Pro, Qwen 3.7 Max and others4
    AbstractStateWise 在动作前修复失效的持久前提。

    StateWise 是在执行带副作用的动作之前，诊断并修复编码智能体持久操作状态的框架。

    Paper analysisRead analysis
  4. 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
You have reached the end