跳到正文
TakoAPI
返回技能列表

agentgate-security

由 wiserautomation 提供

Coding Agents & IDEs
357下载量由 clawskills.sh 提供
1浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

displayName: AgentGate - Enterprise Security Firewall for OpenClaw.

描述

该技能的功能

AgentGate is a middleware layer that intercepts every tool call an OpenClaw agent makes before it executes. It evaluates each call against regex-based policies stored in Firestore and returns ALLOW, DENY, or REQUIRE_APPROVAL. Blocked actions return a structured error; approvals pause execution until an operator responds.

Policies are enforced before tool execution, so a hallucinating agent cannot bypass rules by retrying or rephrasing the same call.

何时使用

  • Blocking destructive bash commands like rm -rf in automated agent pipelines
  • Requiring human approval before Stripe charges exceed a set dollar threshold
  • Restricting outbound HTTP requests to a whitelist of approved domains
  • Auditing every agent tool call in real time with a live Firestore log
  • Preventing agents from sending unauthorized emails via SMTP or SendGrid

示例工作流

输入

User asks: Process a $500 refund for customer order #9821

智能体
  1. 1

    Agent invokes the stripe tool with a charge amount of 50000

  2. 2

    AgentGate intercepts the call and POSTs the tool name and serialized arguments to the Firebase Cloud Function

  3. 3

    Function validates the API key, evaluates regex policies, and matches the amount against the approval threshold rule

  4. 4

    Decision is REQUIRE_APPROVAL; a Telegram webhook fires to the operator with Approve/Deny buttons

  5. 5

    Operator approves; Firestore updates and the agent resumes execution

输出

Stripe refund completes after human approval, with the full interaction recorded in the audit log

前置要求

  • AgentGate account at agent-gate-rho.vercel.app
  • AGENTGATE_API_KEY environment variable

安装

clawhub install wiserautomation/agentgate-security

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接