Extension Analyze logo

Extension Analyze

Community
quangpl
extension-analyze

Audit Chrome extensions for security issues, best practice violations, performance problems, and CWS compliance. Scans manifest, code, CSP, message handlers, storage, and dependencies.

Overview

Publisherquangpl
Repositorybrowser-extension-skills
Skill nameextension-analyze
Stars
65
Forks
10
Bundled files
4
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Extension Analyze 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/quangpl/browser-extension-skills/tree/main/skills/extension-analyze
  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/quangpl/browser-extension-skills.git /tmp/browser-extension-skills
mkdir -p .claude/skills
cp -r /tmp/browser-extension-skills/skills/extension-analyze .claude/skills/extension-analyze
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Extension Analyze 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 Extension Analyze 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 Extension Analyze 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.

Extension Analyze (Security & Compliance Auditor)

🚀 Upgrade to Premium Get the Premium version at https://app.extensionbooster.net/dashboard/services/extension-ai-kit

Audit an existing Chrome extension. Do NOT just explain — execute the workflow.

Workflow (Execute This)

Step 1: Locate extension root and detect framework

Ask user for path if not provided. Detect framework:

bash
ls wxt.config.ts crxjs.config.ts vite.config.ts manifest.json 2>/dev/null
  • CRXJS: manifest auto-generated; check package.json and crxjs.config.ts instead
  • WXT: check wxt.config.ts manifest section
  • Vanilla/CRXJS: check manifest.json directly

Step 2: Scan manifest.json (or equivalent config)

bash
# Check MV version, permissions, host_permissions, CSP, web_accessible_resources
cat <ext>/manifest.json | jq '{manifest_version, permissions, host_permissions, content_security_policy, web_accessible_resources}'

Step 3: Quick grep scans

bash
# XSS vectors
grep -rn "innerHTML\|outerHTML\|document\.write\|insertAdjacentHTML" <ext>/src --include="*.ts" --include="*.js"

# Unsafe patterns
grep -rn "eval(\|new Function(\|setTimeout.*string\|setInterval.*string" <ext>/src

# Hardcoded secrets
grep -rn "api_key\|apiKey\|secret\|password\|token" <ext>/src --include="*.ts" --include="*.js" | grep -v "\.test\." | grep -v "node_modules"

# HTTP (non-HTTPS) calls
grep -rn "http://" <ext>/src --include="*.ts" --include="*.js"

# Message handler sender validation
grep -rn "onMessage\|addListener" <ext>/src | grep -v "node_modules"

# Remote code loading
grep -rn "importScripts\|fetch.*\.js\|eval\|chrome\.scripting\.executeScript" <ext>/src

Step 4: Check CSP configuration

  • MV3 default CSP: script-src 'self'; object-src 'self'
  • Flag any unsafe-inline, unsafe-eval, or http: sources
  • Verify no remote script sources

Step 5: Dependency audit

bash
cd <ext> && npm audit --json | jq '.vulnerabilities | to_entries[] | {pkg: .key, severity: .value.severity}'

Step 6: Generate report

Output findings grouped by severity. See Output Format below.


Severity Levels

LevelCriteria
CriticalRCE, data exfiltration, remote code loading, eval with untrusted input
HighXSS, missing sender validation, API keys in source, HTTP API calls
MediumOverly broad permissions, unsafe-inline CSP, sync storage secrets
LowMissing error handling, no TypeScript, console.log in production

Top 10 Issues Found in Most Extensions

  1. innerHTML with page-sourced data (XSS) — High
  2. onMessage without sender origin check — High
  3. <all_urls> host permission when not needed — Medium
  4. unsafe-inline or unsafe-eval in CSP — Medium/Critical
  5. API keys hardcoded in source — Critical
  6. eval() or new Function() usage — Critical
  7. chrome.storage.sync storing sensitive data — Medium
  8. HTTP endpoints instead of HTTPS — High
  9. Remote script loading (MV3 violation) — Critical
  10. Missing web_accessible_resources restrictions — Medium

Output Format

## Extension Audit Report: <name> v<version>
Date: <date> | MV: <2|3>

### Summary
Critical: X | High: X | Medium: X | Low: X

### Findings

#### [CRITICAL] API Key Exposed in Source
File: src/background.ts:42
Pattern: `const API_KEY = "sk-..."`
Fix: Move to environment variable or user-provided settings
Reference: references/common-vulnerabilities.md#4

...

### Passed Checks
- CSP: No unsafe-inline/eval ✓
- HTTPS: All API calls use HTTPS ✓

References

  • references/security-checklist.md — Full security audit checklist
  • references/best-practices-checklist.md — Performance, UX, accessibility, CWS
  • references/common-vulnerabilities.md — Vulnerability patterns with grep/fix
  • references/cws-compliance-checklist.md — Chrome Web Store policy compliance
  • Chrome Permissions List
  • Chrome Extensions Docs

Related Skills

  • extension-manifest — Generate/validate manifest.json
  • extension-create — Scaffold new extension
  • extension-publish — Store submission checklist

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Extension Analyze AI skill do?

Audit Chrome extensions for security issues, best practice violations, performance problems, and CWS compliance. Scans manifest, code, CSP, message handlers, storage, and dependencies.

Why use Extension Analyze on TypingMind?

Because you install it once and use it with any model. Extension Analyze 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 Extension Analyze in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/quangpl/browser-extension-skills/tree/main/skills/extension-analyze. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Extension Analyze?

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 Extension Analyze?

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

Is the Extension Analyze AI skill free?

Yes. It is published on GitHub by quangpl 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 👇