Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Impact

Unauthorized actions10Data and privacy leaks2

Attack surface / entry point

User input2Tool responses3Tool and skill descriptions3Inter-agent messages4

System component

MCP and skills5Memory3RAG7Guardrails and judges3Reasoning chains5Permissions and sandboxing2Fine-tuning and open weights3Multimodal5
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.
Impact：Data and privacy leaksAttack surface / entry point：User inputSystem component：Permissions and sandboxingClear all

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

  1. DefensesarXiv 2609.33371

    论文提出保险库中介执行边界，评估 LLM Agent 的 API 凭据处理风险

    提出并评测保险库中介执行边界，隔离 Agent 的 API 凭据

    arXiv
    2609.33371
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Corvic Security Vault
    Abstract作者称，凭据分离可减少披露路径，但权限、操作授权和配置验证仍需独立控制。

    这是一项智能体 API 凭据威胁分析及 Vault 执行边界的功能评测。作者关心的不是模型能否承诺保密，而是认证材料是否会进入模型、日志、记忆和执行代码。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.14003

    FlowSeal：用信息流控制阻断 LLM Agent 的隐私泄露

    提出 FLOWSEAL，用工具级信息流控制阻断智能体隐私泄露

    arXiv
    2609.14003
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V3.2, GPT-4.1-mini, Gemini-Flash-2.5

    Abstract作者分析大模型智能体隐私检查与攻击面重合问题，提出外部拦截防御 FLOWSEAL 并验证有效性。

    Paper analysisRead analysis
You have reached the end