Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Attack type

Prompt injection5

Impact

Unauthorized actions3Data and privacy leaks3

System type

AI Agent6Multi-agent systems4

Attack surface / entry point

User input15Web pages and interfaces7Documents and messages8Tool responses15Tool and skill descriptions53Memory writes6Inter-agent messages6Distribution channels36Inference services and hardware0

Layer

Application layer6

System component

MCP and skills6Memory4Guardrails and judges3Monitors4Permissions and sandboxing8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Inter-agent messagesAttack surface / entry point：Inference services and hardwareSystem component：MCP and skillsClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.03153

    EvoRiskBench：面向工作区 Agent 运行时安全风险的演化基准

    构建 EvoRiskBench 评测工作区 Agent 的运行时安全风险

    arXiv
    2610.03153
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Sol, DeepSeek-V4-Pro-0813, Claude Opus 5

    Abstract论文构建了工作空间智能体运行时风险基准 EvoRiskBench，发现高执行力智能体在 IPI 下面临较高安全风险。

    Paper analysisRead analysis
  2. AttacksarXiv 2610.00430

    Memetic Trojans：利用社交传染在 LLM Agent 网络中传播对抗载荷

    提出 memetic trojans，借助社交传染在 Agent 网络中传播对抗载荷

    arXiv
    2610.00430
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gpt-oss-120B, deepseek-v4.1-flash, qwen-32B and others5
    Abstractmemetic trojans 用内生社会传染携带载荷。

    Memetic trojans 是一类网络介导攻击：对抗载荷搭在智能体本来就会转发和点赞的内容上扩散，转发者不必被攻陷，也不必执行“请继续复制”的指令。

    Paper analysisRead analysis
  3. AttacksarXiv 2610.00392

    A2A-TIBA：针对 A2A 协议 LLM 智能体的间接提示注入攻击与三层同构攻防模型

    提出 A2A-TIBA，经 A2A 对等任务间接注入并植入常驻回调

    arXiv
    2610.00392
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    MiniMax-M3, deepseek-v4-pro, glm-5.3 and others8
    AbstractA2A-TIBA 一次植入后绕过智能体，GDA 用四类结果定位防线，ELA-ITL 把信封标注列为第三层。

    A2A-TIBA 把间接提示注入和绕过放进 A2A：gray-box 攻击者已能投递任务，诱导目标部署常驻回调程序后，下令和外传不再经过智能体。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
  5. DefensesarXiv 2608.30083

    研究者提出零知识谓词证明网关，在 MCP 与 Agent2Agent 上实现 Agent 间数据最小化

    提出 Proof Gateway，用零知识谓词证明实现 Agent 间数据最小化

    arXiv
    2608.30083
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract作者将 source integrity 而不是证明开销视为绑定约束。

    Proof Gateway 是一套已运行的智能体间数据最小化机制：用治理谓词的零知识证明代替原始值和自然语言自述。

    Paper analysisRead analysis
You have reached the end