Global Privacy Control logo

Global Privacy Control

Community
mukul975
global-privacy-control

Implementation guide for Global Privacy Control (GPC) automated opt-out signal per CPRA Section 1798.135(e). Covers Sec-GPC HTTP header detection, JavaScript navigator.globalPrivacyControl API, and state-specific requirements for CA, CO, CT, MT, TX, and OR. Includes server-side detection code and compliance mapping.

Overview

Publishermukul975
RepositoryPrivacy-Data-Protection-Skills
Skill nameglobal-privacy-control
Stars
279
Forks
59
Bundled files
4
LicenseApache-2.0
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 mukul975 on GitHub. Read the source before you install it.

Installation

Install the Global Privacy Control 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/consent-management-skills/skills/global-privacy-control .claude/skills/global-privacy-control
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Global Privacy Control 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 Global Privacy Control 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 Global Privacy Control 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.

Implementing Global Privacy Control (GPC)

Overview

Global Privacy Control (GPC) is a browser-level signal that communicates a user's privacy preference to opt out of the sale or sharing of their personal information. The GPC specification defines both an HTTP header (Sec-GPC: 1) and a JavaScript API (navigator.globalPrivacyControl) for transmitting this signal.

Under California Privacy Rights Act (CPRA) Section 1798.135(e), businesses must treat GPC signals as valid opt-out requests. The California Attorney General confirmed this enforcement position in the Sephora settlement (August 2022, $1.2 million fine), which was the first enforcement action involving GPC signals.

Legal Requirements by State

California — CPRA (effective January 1, 2023)

  • Section 1798.135(e): A business that collects consumers' personal information shall treat the consumer's use of an opt-out preference signal as a valid request to opt out of sale/sharing under Section 1798.120.
  • AG Regulation 11 CCR 7025(b): If a business collects personal information from consumers online, the business shall treat an opt-out preference signal as a valid request to opt-out of sale/sharing for that browser or device and any consumer profile associated with that browser or device.
  • Sephora Settlement (August 2022): California AG fined Sephora $1.2 million for failing to honor GPC signals, among other violations.

Colorado — Colorado Privacy Act (CPA, effective July 1, 2024)

  • Section 6-1-1306(1)(a)(IV)(A): Consumers may exercise the right to opt out through an opt-out preference signal sent by a platform, technology, or mechanism on behalf of the consumer, to the extent technically feasible.
  • CPA Rules 4.6: Controllers must recognize universal opt-out mechanisms by July 1, 2024.

Connecticut — Connecticut Data Privacy Act (CTDPA, effective July 1, 2023)

  • Section 42-520(b)(5): Beginning January 1, 2025, controllers must recognize universal opt-out mechanisms for the sale of personal data and targeted advertising.

Montana — Montana Consumer Data Privacy Act (effective October 1, 2024)

  • Section 30-14-2807: Controllers must recognize opt-out preference signals as valid opt-out requests for the sale of personal data and targeted advertising.

Texas — Texas Data Privacy and Security Act (TDPSA, effective July 1, 2024)

  • Section 541.055: Controllers must allow consumers to opt out of the sale of personal data and targeted advertising. Universal opt-out mechanisms must be honored beginning January 1, 2025.

Oregon — Oregon Consumer Privacy Act (effective July 1, 2024)

  • Section 646A.578: Controllers shall provide a method by which consumers can opt out that includes recognition of opt-out preference signals.

GPC Technical Specification

HTTP Header Detection

The GPC signal is transmitted as an HTTP request header:

Sec-GPC: 1

This header is set by the browser (or browser extension) on every HTTP request when the user has enabled GPC. The header is absent (not set to 0) when GPC is not enabled.

JavaScript API Detection

The GPC signal is also available via the JavaScript DOM API:

javascript
// Check if GPC is supported and enabled
if (navigator.globalPrivacyControl === true) {
    // User has opted out — do not sell/share personal information
    // Do not load non-essential tracking scripts
    // Set internal opt-out flag for this user
}

Key considerations:

  • navigator.globalPrivacyControl returns true when GPC is enabled
  • navigator.globalPrivacyControl returns false or undefined when GPC is not enabled or not supported
  • Check should occur before loading any tracking or advertising scripts

Server-Side Detection (HTTP Header)

On the server side, check for the Sec-GPC header in incoming requests:

If Sec-GPC header is present AND equals "1":
    → Set opt-out flag for this session/user
    → Do not initiate sale or sharing of personal information
    → Do not load third-party tracking pixels
    → Log GPC signal receipt for compliance records

Implementation Architecture at CloudVault SaaS Inc.

Client-Side Detection

CloudVault SaaS Inc. checks GPC at two points:

  1. Page Load: Before initializing any analytics or advertising SDKs, check navigator.globalPrivacyControl. If true, suppress non-essential tracking.

  2. Consent Banner Interaction: If GPC is detected, pre-select the "Opt Out of Sale/Sharing" option in the cookie consent banner and display a notice: "We detected your Global Privacy Control signal. Your opt-out preference has been applied."

Server-Side Processing

The CloudVault SaaS Inc. backend middleware:

  1. Inspects every incoming HTTP request for the Sec-GPC: 1 header.
  2. If detected, sets a session-level flag gpc_opt_out = true.
  3. If the request is associated with an authenticated user, propagates the opt-out to the user's consent record for applicable purposes (sale/sharing).
  4. Returns a Sec-GPC response header echoing the signal (transparency).
  5. Logs the GPC signal receipt with timestamp, user agent, and associated user ID (if authenticated).

Mapping GPC to Internal Consent System

GPC is a binary signal (opt out of sale/sharing). CloudVault SaaS Inc. maps it to specific consent purposes:

GPC SignalInternal PurposeAction
Sec-GPC: 1pur_benchmarking_003 (Third-party data sharing)Withdraw consent / opt out
Sec-GPC: 1pur_advertising_004 (Targeted advertising)Withdraw consent / opt out
Sec-GPC: 1pur_analytics_001 (Service improvement)No change (internal use, not sale/sharing)
Sec-GPC: 1pur_marketing_002 (Product emails)No change (direct marketing, not sale/sharing)

Conflict Resolution

When a user has manually opted in via the preference center but their browser sends GPC:

  • CPRA approach: GPC takes precedence. Per AG regulation 11 CCR 7025(c), if a conflict exists between the opt-out preference signal and the consumer's participation in a financial incentive program, the business shall respect the opt-out preference signal but may notify the consumer of the conflict and give the consumer the choice to confirm their participation.
  • CloudVault SaaS Inc. policy: Display a notification: "Your browser is sending a Global Privacy Control signal to opt out of data sharing. This overrides your previous opt-in. To continue sharing data for industry benchmarking, you can confirm your preference in Settings > Privacy."

Compliance Verification

To verify GPC implementation:

  1. Install a GPC-enabled browser or extension (Firefox with Enhanced Tracking Protection, DuckDuckGo browser, Brave browser, or the OptMeowt extension for Chrome)
  2. Navigate to CloudVault SaaS Inc. application
  3. Verify that Sec-GPC: 1 header is sent in network requests
  4. Confirm that tracking scripts are not loaded
  5. Confirm that the consent banner reflects the opt-out preference
  6. Verify server-side logs record the GPC signal
  7. Confirm that authenticated users have their consent record updated

Key Regulatory References

  • CPRA Section 1798.135(e) — Opt-out preference signal requirement
  • California AG Regulation 11 CCR 7025 — GPC implementation details
  • GPC Specification (globalprivacycontrol.org) — Technical standard
  • Colorado Privacy Act Section 6-1-1306(1)(a)(IV)(A) — Universal opt-out
  • Connecticut CTDPA Section 42-520(b)(5) — Universal opt-out mechanism
  • Montana MCDPA Section 30-14-2807 — Opt-out preference signals
  • Texas TDPSA Section 541.055 — Opt-out methods
  • Oregon OCPA Section 646A.578 — Opt-out preference signals
  • Sephora Settlement (California AG, August 2022) — First GPC enforcement

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 Global Privacy Control AI skill do?

Implementation guide for Global Privacy Control (GPC) automated opt-out signal per CPRA Section 1798.135(e). Covers Sec-GPC HTTP header detection, JavaScript navigator.globalPrivacyControl API, and state-specific requirements for CA, CO, CT, MT, TX, and OR. Includes server-side detection code and compliance mapping.

Why use Global Privacy Control on TypingMind?

Because you install it once and use it with any model. Global Privacy Control 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 Global Privacy Control in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/plugins/consent-management-skills/skills/global-privacy-control. 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 Global Privacy Control?

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 Global Privacy Control?

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

Is the Global Privacy Control 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.

View all

Set up your own AI workspace now

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