Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter5

Attack type

Prompt injection7

Attack technique

Gradient and representation optimization2Automated search24Encoding and obfuscation5Reasoning-chain manipulation3Defense-targeted6Dormant triggers11

Impact

Unauthorized actions4

System type

AI Agent7

Attack surface / entry point

User input10Web pages and interfaces7Documents and messages6Tool responses6Tool and skill descriptions5Code repositories and dependencies2Retrieval corpus8Memory writes3Inter-agent messages3Images, audio and video8Distribution channels5

Layer

Application layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Encoding and obfuscationAttack surface / entry point：Tool responsesAttack surface / entry point：Code repositories and dependenciesLayer：Application layerClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  3. AttacksarXiv 2609.18217

    研究：跨通道碎片化攻击可绕过 MCP 单通道防御

    提出跨通道分段攻击，利用 MCP 隐式信任外发敏感文件

    arXiv
    2609.18217
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4o, GPT-4o-mini, GPT-5.4 and others15

    Abstract论文揭示了 MCP 多通道隐式信任层级，通过跨通道分段与协议级利用突破现有防御，展示了严重的凭证外发风险。

    Paper analysisRead analysis
  5. AttacksarXiv 2606.21732

    研究者提出 relinking 漏洞：LLM Agent 压缩边界可被拼出恶意指令

    提出 Relink 攻击，在 Agent 压缩边界将分散良性片段重组为恶意指令

    arXiv
    2606.21732
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma-4-31B-it, GPT-OSS-20B, Qwen3.6-27B and others15
    Abstract论文指出提示词压缩引入重链漏洞，提出 RELINK 攻击工具与 KBRA 边界审计防御，证明压缩边界应作为关键安全边界。

    本文研究了智能体基于摘要的提示词压缩所引入的新型安全漏洞——重链（Relinking），并提出了系统化的攻击构建方法与边界审计防御机制。

    Paper analysisRead analysis
  6. AttacksarXiv 2509.22040

    研究：通过编码规则文件对Cursor与GitHub Copilot实施提示注入

    通过规则文件提示注入劫持编码编辑器并执行未授权终端命令

    arXiv
    2509.22040
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Cursor, GitHub Copilot, Claude 4 Sonnet and others4

    Abstract论文提出了针对代码编辑器的提示注入评估框架 AIShellJack，实验显示攻击能诱导 AI 执行未授权终端命令。

    Paper analysisRead analysis
  7. AttacksarXiv 2507.10457

    论文提出 LPCI：针对 Agent 逻辑层与持久记忆的提示控制注入攻击

    提出 LPCI，把延迟条件载荷写入记忆与检索库以跨会话触发

    arXiv
    2507.10457
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    ChatGPT, Claude, LLaMA3 and others8
    Abstract作者定义 LPCI。

    作者把LPCI定义为针对智能体逻辑执行、记忆留存和工具集成的跨阶段漏洞类，而不是单次输入上的提示改写。

    Paper analysisRead analysis
You have reached the end