Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter3

Attack technique

Automated search12Multi-turn escalation2Encoding and obfuscation6Cross-modal payloads1Defense-targeted7Dormant triggers7Selection manipulation3

System type

Models and APIs60LLM applications5AI Agent17coding agent3web agent4Embodied systems and robotics3

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack technique：Multi-turn escalationAttack technique：Cross-modal payloadsSystem type：coding agentClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.35912

    MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

    提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作

    arXiv
    2609.35912
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6

    Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。

    Paper analysisRead analysis
  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
You have reached the end