apoer-agent-guardrail
by ClawHub · v1.0.0 · 更新于 2026-03-29T16:32:27+0800
Pre-authorizes AI agent tool calls deterministically using APort policy engine to enforce permissions before execution
技能说明
Pre-action authorization for AI agents. Verifies permissions before every tool runs (shell, messaging, git, MCP, data export). Works with OpenClaw, IronClaw, PicoClaw. APort policy engine allows or denies each tool call deterministically; agent cannot skip it.
中文介绍
AI代理的预行动授权机制。在每次工具调用前验证权限（包括shell、消息、git、MCP、数据导出）。与OpenClaw、IronClaw、PicoClaw兼容。APort策略引擎以确定性方式允许或拒绝每个工具调用，代理无法跳过此验证。
安装步骤
直接复制以下提示词，发送给你的 AI 助手即可完成安装。
帮我下载并安装这个SKILL：https://skillhub.cstcloud.cn/download/apoer-agent-guardrail
点击右上角 下载SKILL 按钮
元信息
分类：Test & Security
下载：4
浏览：6
标签：
pre-action authorization
tool call policy
deterministic access control