Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 1 paper
Filter3

Attack type

Prompt injection6Poisoning and backdoors1

System component

MCP and skills9Memory10Monitors1Permissions and sandboxing11Multimodal0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack type：Poisoning and backdoorsSystem component：MonitorsSystem component：MultimodalTopic: Agent safetyClear all
  1. DefensesarXiv 2608.21101

    ClawSentry：面向自主 LLM Agent 的渐进式多层安全监控网关

    提出 ClawSentry 多层监控网关，在技能准入和运行时拦截恶意技能与隐藏指令

    arXiv
    2608.21101
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Codex/GPT-5.4, Codex/GPT-5.5, Claude Code/GLM-5.1 and others6
    AbstractClawSentry 用包准入、三级运行时门控和反绕过，压低 skill 攻击并保住干净任务。

    ClawSentry 是挂在智能体运行时之外的安全监督网关，用来同时盖住 skill 执行的多个生命周期边界，并把已被拒绝的效果记到会话里。

    Paper analysisRead analysis
You have reached the end