Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter5

Attack type

Prompt injection3Poisoning and backdoors4

Attack technique

Dormant triggers3

System type

AI Agent47coding agent4Multi-agent systems7

Attack surface / entry point

User input1Documents and messages1Memory writes3

Layer

Application layer4

System component

MCP and skills6Memory4Monitors7Permissions and sandboxing3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
System type：coding agentAttack surface / entry point：User inputAttack surface / entry point：Documents and messagesAttack surface / entry point：Memory writesSystem component：MemoryClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.13889

    PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击

    提出 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私

    arXiv
    2609.13889
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    DeepSeek-V4-Flash, DeepSeek-V4-Pro, Qwen3-Max

    Abstract论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。

    Paper analysisRead analysis
  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
You have reached the end