npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@wd041216-bit/ironclaw-agent-guard

v0.5.0

Published

Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.

Readme

IronClaw Agent Guard

面向可调用工具的 AI agent 运行时的轻量安全护栏:在真正造成破坏之前,先扫描高风险载荷、脱敏秘密信息并留下审计轨迹。

For English docs, see README.md.

这个仓库是从 OpenClaw 专用安全插件中抽出来的通用核心,目标是让 CLI、MCP server、Claude Code skills、Manus skills 和各类运行时适配层都能复用同一套安全能力。

这个仓库解决什么问题

带工具的 agent 往往会在这些地方出问题:

  • 危险 shell 命令执行得太早
  • prompt injection 改写工具行为
  • token / secret 被发到聊天、Webhook 或 HTTP 请求里
  • 敏感路径被暴露到工具参数中

ironclaw-agent-guard 提供的是一层轻量安全基线,而不是沙箱、容器或者恶意软件隔离系统。

它提供什么

  • shell / file / network / messaging 载荷扫描
  • prompt injection 模式检测
  • secret 检测与脱敏
  • 敏感路径与路径穿越检查
  • 出站 host allowlist 检查
  • JSONL 审计日志 helper
  • 可直接使用的 CLI
  • 可嵌入运行时的 SDK

快速开始

安装:

npm install @wd041216-bit/ironclaw-agent-guard

扫描一个危险 shell 命令:

ironclaw-guard scan --tool shell --content "rm -rf /tmp/demo"

从 stdin 脱敏 secret:

printf 'Bearer abcdefghijklmnopqrstuvwxyz123456' | ironclaw-guard redact --stdin

Claude Code / Agent Skills

这个仓库现在已经自带了可直接复用的技能资产:

最短安装方式:

mkdir -p .claude/skills
cp -R skills/ironclaw-agent-guard .claude/skills/

MCP server

这个包现在同时提供 stdio 和 Streamable HTTP 两种 MCP 形态,默认提供两个工具:

  • security_scan
  • redact_text

本地 stdio 启动:

npx @wd041216-bit/[email protected] ironclaw-guard-mcp

远程 HTTP MCP 启动:

npx @wd041216-bit/[email protected] ironclaw-guard-mcp-http --host 0.0.0.0 --port 3001

集成说明见 docs/mcp.md

Manus

Manus 已支持直接从 GitHub 导入 Skill。这个仓库现在补了根目录 SKILL.mddocs/manus.md,可以直接作为一个可导入的安全审查技能仓库使用。

适合接入的场景

  • OpenClaw 插件适配层
  • Claude Code / Agent Skills
  • Manus Skills
  • MCP 安全工具包装
  • CI / preflight 风险检查
  • 自定义 Node.js agent runtime

非目标

这个仓库提供:

  • 进程隔离
  • 容器或 WASM 沙箱
  • 恶意软件完全防护
  • 替代操作系统、网络和凭据治理

仓库结构

和 OpenClaw 的关系

这个仓库是通用核心。OpenClaw 专用 adapter、plugin manifest 和 bundled skill 更适合继续留在单独的 OpenClaw 仓库里。

License

MIT