Npm Security logo

Npm Security

Community
bodadotsh
npm-security

Prevent JavaScript/TypeScript projects from supply-chain attacks across package managers like npm, pnpm, yarn, bun, and deno. Use whenever planning, installing, updating dependencies or configuring package managers

Overview

Publisherbodadotsh
Repositorynpm-security-best-practices
Skill namenpm-security
Stars
857
Forks
19
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bodadotsh on GitHub. Read the source before you install it.

Installation

Install the Npm Security AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bodadotsh/npm-security-best-practices/tree/main/skills/npm-security
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bodadotsh/npm-security-best-practices.git /tmp/npm-security-best-practices
mkdir -p .claude/skills
cp -r /tmp/npm-security-best-practices/skills/npm-security .claude/skills/npm-security
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Npm Security in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Npm Security on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Npm Security is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Apply the following security best practices. NEVER override an explicit user opt-in config (lifecycle scripts, cooldowns, save prefix, etc) unless they ask. Always check current package manager's verions, and verify against their official documentations.

Best Practices

Best practices are safer and sensible environmental defaults that should be enabled for the agent's runtime, we are using npm as example here but you should check to see which package manager is available and apply the configurations according.

Lifecycle scripts

Unless explicitly defined otherwise, package managers should have lifecycle scripts set as off, for example preinstall and postinstall.

In .npmrc, this can be set as ignore-scripts=true, or through install command: npm install --ignore-scripts <package>.

Dependency cooldowns / minimum release age

Unless explicitly defined otherwise, dependency installations should respect a cooldown period (default to 3 days).

In .npmrc, this can be set as min-release-age=3, or through install command npm install --min-release-age=3 <package>.

Exact versions

Unless explicitly defined otherwise, package installations should install the expact version instead of a semver range.

In .npmrc, this can be set as save-exact=true, or through install command npm install --save-exact <package>

Persist these defaults in the project .npmrc (or the package manager’s equivalent), merging only keys that are unset; never overwrite existing values unless the user asks.

Planning stage / package scorers

When planning third-party dependencies, we should score package candidates first. This reduces risk of greyware (not malware, but can be trollware, abandonware, low quality, license changes, etc).

Few free and trustworthy scorers are:

For example, Socket MCP server can be figured as:

json
{
  "mcpServers": {
    "socket-mcp": {
      "type": "http",
      "url": "https://mcp.socket.dev/"
    }
  }
}

Once installed, use the MCP to ask questions like:

  • "Check the security score for express version 4.18.2"
  • "Analyze the security of my package.json dependencies"
  • "What are the vulnerability scores for react, lodash, and axios?"

The user should set a policy of when to reject dependencies based on their health metrics (quality, supply chain, maintenance, etc), else default to a sensible number (e.g., 80).

Install stage / package scanners

When it is time to install third-party dependencies, we should wrap the installation command with a package scanner first. This reduces risk of compromises as the scanner will check against a real-time intelligence database.

Few free and trustworthy scanners are:

FOr example, the sfw cli can be downloaded first through npm i -g sfw or through npx: npx sfw npm install <package>

Even as a popular and well-known package passes the planning/scoring stage, the installation/scanning stage can catch it if they get compromised.

References

Frequently asked questions

What does the Npm Security AI skill do?

Prevent JavaScript/TypeScript projects from supply-chain attacks across package managers like npm, pnpm, yarn, bun, and deno. Use whenever planning, installing, updating dependencies or configuring package managers

Why use Npm Security on TypingMind?

Because you install it once and use it with any model. Npm Security is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Npm Security in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bodadotsh/npm-security-best-practices/tree/main/skills/npm-security. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Npm Security?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Npm Security?

As many as you like. As long as a model supports skills, you can use Npm Security with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Npm Security AI skill free?

Yes. It is published on GitHub by bodadotsh under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇