跳到正文
TakoAPI
返回技能列表

vigil

由 robinoppenstam 提供

Git & GitHub
729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

AI agent safety guardrails for tool calls.

描述

该技能的功能

Vigil validates AI agent tool calls before they execute, blocking operations like destructive shell commands, SSRF, SQL injection, path traversal, and credential leaks. It runs as a drop-in npm package with 22 rules, zero runtime dependencies, and under 2ms latency per check.

Zero runtime dependencies and sub-2ms latency mean it can run inline on every tool call without adding measurable overhead to the agent pipeline.

何时使用

  • Blocking rm -rf commands issued by autonomous agents
  • Preventing SSRF in agent-driven API and HTTP calls
  • Catching SQL injection before a database tool executes
  • Auditing all tool calls made by a shell-executing agent
  • Adding a safety layer to an existing MCP server

示例工作流

输入

User asks: validate a shell command before my agent runs it

智能体
  1. 1

    Import checkAction from vigil-agent-safety

  2. 2

    Pass the tool name and params object to checkAction

  3. 3

    Receive a decision (ALLOW, BLOCK, or ESCALATE) with a reason string

  4. 4

    Block execution or proceed based on the returned decision

输出

BLOCK: Destructive command pattern — the rm -rf / call is rejected before execution

前置要求

  • vigil-agent-safety npm package

安装

clawhub install robinoppenstam/vigil

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