Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack type

Prompt injection3

Impact

Unauthorized actions12Data and privacy leaks5Output manipulation3

System type

LLM applications16AI Agent21coding agent3Multi-agent systems7

Attack surface / entry point

Documents and messages0Code repositories and dependencies3Memory writes0Distribution channels3
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.
Impact：Output manipulationSystem type：coding agentAttack surface / entry point：Documents and messagesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Memory writesClear all

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

  1. AttacksarXiv 2610.09264

    研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击

    提出 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包

    arXiv
    2610.09264
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
    AbstractPackHallu 诱导规则文件换包。

    PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。

    Paper analysisRead analysis
You have reached the end