Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Impact

Harmful content1Unauthorized actions12Data and privacy leaks4Output manipulation3

System type

AI Agent7coding agent1

Attack surface / entry point

User input4Tool responses0Code repositories and dependencies1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Impact：Harmful contentSystem type：coding agentAttack surface / entry point：Tool responsesAttack surface / entry point：Code repositories and dependenciesClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2510.01359

    JAWS-Bench：研究者用三种工作区场景系统越狱代码 Agent

    提出 JAWS-Bench，评测代码 Agent 在三级工作区中的越狱与恶意代码可执行性

    arXiv
    2510.01359
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4.1, GPT-o1, DeepSeek-R1 and others8

    Abstract论文提出了评估代码智能体端到端恶意代码越狱的 JAWS-Bench，发现多文件与智能体推理会明显放大可部署危害。

    Paper analysisRead analysis
You have reached the end