Cookie Audit logo

Cookie Audit

Community
mukul975
cookie-audit

Comprehensive methodology for auditing website cookies and tracking technologies. Covers automated scanning, cookie categorization, lifecycle documentation, and compliance gap analysis referencing the Planet49 CJEU ruling (C-673/17).

Overview

Publishermukul975
RepositoryPrivacy-Data-Protection-Skills
Skill namecookie-audit
Stars
279
Forks
59
Bundled files
4
LicenseApache-2.0
Links
Skill sourceRepository
  • 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 mukul975 on GitHub. Read the source before you install it.

Installation

Install the Cookie Audit 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.
  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/mukul975/Privacy-Data-Protection-Skills.git /tmp/Privacy-Data-Protection-Skills
mkdir -p .claude/skills
cp -r /tmp/Privacy-Data-Protection-Skills/plugins/cookie-consent-skills/skills/cookie-audit .claude/skills/cookie-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cookie Audit 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 Cookie Audit 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 Cookie Audit 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.

Auditing Website Cookies and Trackers

Overview

A cookie audit is the foundational step in achieving cookie consent compliance. It involves systematically identifying, categorizing, and documenting every cookie and tracking technology deployed on a website. The Court of Justice of the European Union in Planet49 GmbH v. Bundesverband der Verbraucherzentralen (Case C-673/17, 1 October 2019) established that pre-ticked checkboxes do not constitute valid consent under the ePrivacy Directive, and that users must be informed about cookie duration and third-party access before consenting. A thorough audit reveals what consent must be obtained and what disclosures must be made.

Audit Methodology

Phase 1: Preparation

Before scanning, document the audit scope for Pinnacle E-Commerce Ltd:

ParameterValue
Primary domainwww.pinnacle-ecommerce.com
Subdomains in scopeshop.pinnacle-ecommerce.com, account.pinnacle-ecommerce.com, blog.pinnacle-ecommerce.com
Authenticated pagesYes — customer account, checkout flow
Mobile-specific pagesm.pinnacle-ecommerce.com
Third-party integrationsGoogle Analytics 4, Meta Pixel, Hotjar, Stripe, Intercom
Scan frequencyQuarterly (next: Q2 2026)

Phase 2: Automated Scanning

Deploy scanning tools to capture all cookies and tracking technologies:

Browser-Based Scanning

Use a headless Chromium instance to crawl the site and capture:

  • First-party cookies set via Set-Cookie headers
  • First-party cookies set via document.cookie JavaScript API
  • Third-party cookies from embedded resources
  • LocalStorage and SessionStorage entries
  • IndexedDB databases
  • Pixels and beacons (1x1 image requests, navigator.sendBeacon() calls)
  • Browser fingerprinting scripts (canvas, WebGL, AudioContext)

Network-Level Capture

Monitor HTTP/HTTPS traffic to identify:

  • Tracking parameters in URL query strings (utm_*, fbclid, gclid)
  • Redirect chains through tracking domains
  • Cookie syncing between third parties
  • Server-to-server data sharing endpoints

Phase 3: Cookie Categorization

Classify each cookie using the ICC UK Cookie Guide categories, aligned with the ePrivacy Directive Article 5(3):

Category 1: Strictly Necessary Cookies essential for the website to function. No consent required under Article 5(3) exemption.

Examples for Pinnacle E-Commerce Ltd:

Cookie NameDomainDurationPurpose
session_id.pinnacle-ecommerce.comSessionMaintains user session state
csrf_token.pinnacle-ecommerce.comSessionCross-site request forgery protection
cart_itemsshop.pinnacle-ecommerce.com24 hoursShopping cart contents
auth_tokenaccount.pinnacle-ecommerce.com30 minutesAuthentication state
load_balancer.pinnacle-ecommerce.comSessionServer load distribution

Category 2: Performance/Analytics Cookies that collect aggregate usage data. Consent required.

Cookie NameDomainDurationPurpose
_ga.pinnacle-ecommerce.com2 yearsGoogle Analytics client ID
_ga_XXXXXXX.pinnacle-ecommerce.com2 yearsGA4 session persistence
_gid.pinnacle-ecommerce.com24 hoursGA4 session distinction
hjSessionUser*.pinnacle-ecommerce.com1 yearHotjar user identification
hjSession*.pinnacle-ecommerce.com30 minutesHotjar session data

Category 3: Functionality Cookies that remember user preferences. Consent required unless strictly necessary.

Cookie NameDomainDurationPurpose
locale.pinnacle-ecommerce.com1 yearLanguage preference
currencyshop.pinnacle-ecommerce.com1 yearCurrency selection
recently_viewedshop.pinnacle-ecommerce.com30 daysRecently viewed products

Category 4: Targeting/Advertising Cookies used for ad targeting and cross-site tracking. Consent always required.

Cookie NameDomainDurationPurpose
_fbp.pinnacle-ecommerce.com90 daysMeta Pixel browser ID
_fbc.pinnacle-ecommerce.com90 daysMeta click identifier
_gcl_au.pinnacle-ecommerce.com90 daysGoogle Ads conversion linker
IDE.doubleclick.net13 monthsGoogle ad serving
fr.facebook.com90 daysMeta ad delivery and measurement

Phase 4: Gap Analysis

For each cookie identified, verify against Planet49 requirements:

Planet49 Compliance Checklist:

  1. Active consent mechanism: Is consent collected via affirmative action (click, toggle), not pre-ticked boxes? (Planet49, para. 62)
  2. Pre-consent information: Before consent is given, is the user informed of:
    • Cookie duration? (Planet49, para. 81)
    • Whether third parties have access? (Planet49, para. 81)
    • The specific purpose of each cookie category?
  3. Granularity: Can users consent to cookie categories individually, not just accept all?
  4. No cookie walls: Is site access available without consenting to non-essential cookies?
  5. Withdrawal mechanism: Can users withdraw consent as easily as they gave it?

Gap Analysis Template:

CookieCategoryConsent CollectedDuration DisclosedThird-Party DisclosedGap
_gaAnalyticsYesNo — listed as "persistent" not "2 years"No — Google not namedDuration + third-party disclosure
_fbpTargetingYesYesYesNone
localeFunctionalityNoNoN/AAssess if strictly necessary

Phase 5: Reporting

The audit report for Pinnacle E-Commerce Ltd must include:

  1. Executive summary: Total cookies found, breakdown by category, critical gaps
  2. Complete cookie inventory: Full table with name, domain, duration, purpose, category, legal basis
  3. Third-party tracker inventory: All third-party domains receiving data, with data types shared
  4. Compliance gap register: Each gap, severity (high/medium/low), remediation recommendation
  5. Cookie policy update recommendations: Specific text changes needed
  6. Consent mechanism assessment: Whether current banner meets Planet49 requirements
  7. Recommended scan schedule: Quarterly for production, on-demand for new feature deployments

Ongoing Monitoring

Schedule automated scans to detect new cookies introduced by:

  • Developer deployments (new analytics or marketing tags)
  • Third-party script updates (vendor SDK updates adding new cookies)
  • A/B testing platforms adding experiment cookies
  • CDN or infrastructure changes

Integrate cookie scanning into the CI/CD pipeline: any new cookie detected in staging must be categorized and documented before deployment to production.

Key Legal References

  • CJEU Case C-673/17 (Planet49) — Active consent required; pre-ticked boxes invalid; cookie duration and third-party access must be disclosed before consent
  • ePrivacy Directive 2002/58/EC, Article 5(3) — Consent required for storing/accessing information on user devices, with strictly necessary exemption
  • GDPR Article 4(11) — Definition of consent: freely given, specific, informed, unambiguous indication
  • EDPB Guidelines 05/2020 on Consent — Detailed guidance on valid consent mechanisms
  • ICC UK Cookie Guide (2012) — Cookie categorization framework (strictly necessary, performance, functionality, targeting)
  • CNIL Deliberation No. 2020-091 (17 September 2020) — Guidelines on cookies and other trackers

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 Cookie Audit AI skill do?

Comprehensive methodology for auditing website cookies and tracking technologies. Covers automated scanning, cookie categorization, lifecycle documentation, and compliance gap analysis referencing the Planet49 CJEU ruling (C-673/17).

Why use Cookie Audit on TypingMind?

Because you install it once and use it with any model. Cookie Audit 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 Cookie Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/plugins/cookie-consent-skills/skills/cookie-audit. 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 Cookie Audit?

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 Cookie Audit?

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

Is the Cookie Audit AI skill free?

Yes. It is published on GitHub by mukul975 under the Apache-2.0 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.

Related AI Skills

View all
mattpocock logo

Codebase Design

mattpocock
CommunityPopular

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or…

22.3K
264.4K
3 files
View
mattpocock logo

Diagnosing Bugs

mattpocock
CommunityPopular

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

22.3K
264.4K
2 files
View
mattpocock logo

Implement

mattpocock
CommunityPopular

Implement a piece of work based on a spec or set of tickets.

22.3K
264.4K
1 files
View
mattpocock logo

Improve Codebase Architecture

mattpocock
CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

22.3K
264.4K
2 files
View

Set up your own AI workspace now

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