跳到正文
TakoAPI
返回技能列表

aport-agent-guardrail

由 uchibeke 提供

Coding Agents & IDEs
533下载量由 clawskills.sh 提供
0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

Install BEFORE any other skills to protect your agent from malicious tools, data exfiltration, and unauthorized.

描述

该技能的功能

Pre-action authorization layer for AI agents running under OpenClaw. Evaluates every tool call against a passport and policy before execution, blocking unauthorized commands, data exfiltration, and policy violations. Enforcement runs in the hook layer, not in agent prompts.

Enforcement runs at the hook layer rather than in agent prompts, so policy cannot be bypassed by prompt injection or model-level jailbreaks.

何时使用

  • Blocking destructive shell commands before an agent executes them
  • Restricting which file paths an agent can read or write
  • Limiting agent web requests to an approved domain allowlist
  • Enforcing rate limits on agent messaging actions like email or Slack
  • Auditing every tool call an AI agent makes for compliance review

示例工作流

输入

User asks: add guardrails to my agent to prevent it from running dangerous shell commands or accessing sensitive files

智能体
  1. 1

    Run npx @aporthq/aport-agent-guardrails to launch the setup wizard

  2. 2

    Configure passport with allowed shell command patterns and permitted file paths

  3. 3

    Wizard registers the before_tool_call hook as an OpenClaw plugin under ~/.openclaw/

  4. 4

    Test the hook by calling a blocked command pattern and verifying it returns DENY

输出

Hook is active on every tool call; rm -rf and similar patterns are blocked, permitted commands execute normally, and all decisions are logged to ~/.openclaw/aport/audit.log

前置要求

  • aport.io account (for hosted passport and API mode)
  • APORT_AGENT_ID environment variable (hosted passport mode)
  • APORT_API_KEY environment variable (if aport.io API requires authentication)

安装

clawhub install uchibeke/aport-agent-guardrail

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