Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Attack type

Prompt injection4

Attack technique

Automated search6Encoding and obfuscation2Defense-targeted2Dormant triggers5

Impact

Unauthorized actions4

System type

AI Agent4

Attack surface / entry point

User input17Web pages and interfaces3Documents and messages5Tool responses7Tool and skill descriptions11Code repositories and dependencies4Retrieval corpus4Memory writes5Distribution channels11

Layer

Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationAttack technique：Defense-targetedAttack surface / entry point：Code repositories and dependenciesLayer：Application layerClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  3. AttacksarXiv 2609.22510

    特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent

    提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse

    arXiv
    2609.22510
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
    Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。

    论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。

    Paper analysisRead analysis
  4. 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
You have reached the end