Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter4

Attack technique

Encoding and obfuscation0Dormant triggers1

System type

LLM applications3AI Agent9coding agent1

Attack surface / entry point

Documents and messages1Tool and skill descriptions7Code repositories and dependencies3Weights and gradients3Distribution channels8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationAttack technique：Dormant triggersSystem type：coding agentAttack surface / entry point：Documents and messagesClear all

Another 216papers 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
You have reached the end