Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 2 papers
Filter3

Attack surface / entry point

User input4Documents and messages1Tool responses2

System component

MCP and skills8Memory5Guardrails and judges3Monitors2Permissions and sandboxing24
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack surface / entry point：Documents and messagesAttack surface / entry point：Tool responsesSystem component：MonitorsTopic: Agent safetyClear all
  1. DefensesarXiv 2609.35659

    Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统

    提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改

    arXiv
    2609.35659
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (claude -p, version 2.1), 独立评审（同一 CLI，无工具）
    AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。

    Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。

    Paper analysisRead analysis
You have reached the end