Skip to content

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

Oct 13 · Tuesday

All papers

Found 5 papers
Filter6

Attack type

Prompt injection4Poisoning and backdoors5

Attack technique

Dormant triggers3

Impact

Unauthorized actions4

System type

AI Agent37coding agent3web agent1Multi-agent systems5Embodied systems and robotics1

Attack surface / entry point

User input3Web pages and interfaces3Code repositories and dependencies3Memory writes5

Layer

Application layer5

System component

Memory5Reasoning chains0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：web agentSystem type：Embodied systems and roboticsAttack surface / entry point：Memory writesSystem component：MemorySystem component：Reasoning chainsClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  4. Evaluation and benchmarksarXiv 2607.14611

    论文评测 Claude Code 与 Codex 记忆文件中的提示注入风险

    评测编码 Agent 记忆文件中提示注入的跨会话影响

    arXiv
    2607.14611
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2 and others4
    Abstract已植入记忆文件的载荷可以跨会话影响 Claude Code 与 Codex，攻击成功与载荷是否留下是两种不同的失败。

    Bad Memory 在沙箱合成工作区里评测文件型持久记忆上的提示注入，比较载荷能否改变当前会话，以及能否在后续会话中留下或叠加。

    Paper analysisRead analysis
  5. 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