Skip to content

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

EventPast event

Harvey 构建 MCP 策略引擎防护提示注入

1 reports1 reporting sourcesLatest report

Start here

AI overview

Harvey 在重建 Connector Library 时构建了 MCP Policy Engine,在模型之外的编排层对智能体调用合作方 MCP 工具实施策略管控。该引擎针对工具投毒和 rug-pull 两类攻击,从工具参数的“承载量”与“权限”两个维度评估信息流,并配合集成期的内部 MCP 安全分析工具检查认证配置、暴露能力与 JSON schema。Harvey 认为安全训练、内容标记与分类器等缓解措施可被绕过,因此主要依赖架构层面的管控。

Generated by AI from reports · Updated 5 days ago

Progress timeline

Oct 7
  1. Harvey
    Harvey 构建 MCP Policy Engine,为智能体调用第三方 MCP 工具加运行时管控

    Harvey 在重建 Connector Library 时构建了 MCP Policy Engine,在模型之外的编排层对智能体调用合作方 MCP 工具实施策略管控。该引擎针对工具投毒和 rug-pull 两类攻击,从工具参数的"承载量"与"权限"两个维度评估信息流,并配合集成期的内部 MCP 安全分析工具检查认证配置、暴露能力与 JSON schema。Harvey 认为安全训练、内容标记与分类器等缓解措施可被绕过,因此主要依赖架构层面的缓解手段。

Related discussion

No discussion links have been collected for this event yet.

Attention trend

New sources per day

7 days total1 ·Maximum1(Oct 7)·Today0

  • Oct 7New1 sources (1 outlets,0 accounts)
  • Oct 8New0 sources (0 outlets,0 accounts)
  • Oct 9New0 sources (0 outlets,0 accounts)
  • Oct 10New0 sources (0 outlets,0 accounts)
  • Oct 11New0 sources (0 outlets,0 accounts)
  • Oct 12New0 sources (0 outlets,0 accounts)
  • Oct 13New0 sources (0 outlets,0 accounts)

Hourly attention

Current attention30·Peak in the comparable period34(Oct 8 01:00)·Change over the comparable past 24 hours 0%

010203040Oct8Oct9Oct11Oct13