Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter6

Attack technique

Encoding and obfuscation1

System type

Models and APIs0LLM applications3AI Agent4coding agent1Embodied systems and robotics0

Attack surface / entry point

User input45Documents and messages0Tool responses1Tool and skill descriptions4Images, audio and video15Weights and gradients3Distribution channels5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationSystem type：Models and APIsSystem type：coding agentSystem type：Embodied systems and roboticsAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool responsesClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  1. 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
You have reached the end