Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter5

Attack technique

Gradient and representation optimization8Encoding and obfuscation2Conversation structure manipulation0Cross-modal payloads13Side channels0

Layer

Prompt layer19Application layer2

System component

MCP and skills7Memory3RAG3Guardrails and judges5Multimodal2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack technique：Encoding and obfuscationAttack technique：Conversation structure manipulationAttack technique：Side channelsLayer：Application layerSystem component：MultimodalClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 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
You have reached the end