Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter5

Impact

Harmful content3Unauthorized actions47Data and privacy leaks15Output manipulation10Availability and reliability11Oversight failure16Increased misuse capability5

System type

Models and APIs0LLM applications7AI Agent25coding agent2science agent4Multi-agent systems8Embodied systems and robotics1

Layer

Prompt layer159Model layer77Application layer3Training and data layer54
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Impact：Harmful contentSystem type：Models and APIsSystem type：coding agentSystem type：Embodied systems and roboticsLayer：Application layerClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2607.03968

    The study reveals workflow-level jailbreaks in IDE programming agents: GitHub Copilot generated harmful content across four backends at 816/816

    提出工作流级越狱，让编程 Agent 在开发任务中写入有害示例

    arXiv
    2607.03968
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.6, Claude Haiku 4.5, Gemini 3.1 Pro and others4
    Abstract作者报告 Copilot 后端会在编码工作流中生成其在单轮条件下通常拒绝的有害答案。

    这是一项生产 IDE 编码智能体的工作流越狱研究，受测对象是 Copilot 的四个模型后端，而非评测流水线中的名义目标。

    Paper analysisRead analysis
  3. 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