Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Attack technique

Gradient and representation optimization0Multi-turn escalation1

Impact

Harmful content1Availability and reliability0

System type

Models and APIs43AI Agent8coding agent1Embodied systems and robotics3
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.
Attack technique：Gradient and representation optimizationAttack technique：Multi-turn escalationImpact：Harmful contentImpact：Availability and reliabilitySystem type：coding agentClear all

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

  1. 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
You have reached the end