Legit Interest Vs Consent logo

Legit Interest Vs Consent

Community
mukul975
legit-interest-vs-consent

Decision framework for choosing between consent and legitimate interest as the lawful basis for processing. Covers power imbalance indicators, conditionality prohibition under Article 7(4), granularity requirements, the three-part LIA test (purpose, necessity, balancing), and practical decision trees for common scenarios.

Overview

Publishermukul975
RepositoryPrivacy-Data-Protection-Skills
Skill namelegit-interest-vs-consent
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 Legit Interest Vs Consent 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/legit-interest-vs-consent .claude/skills/legit-interest-vs-consent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Legit Interest Vs Consent 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 Legit Interest Vs Consent 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 Legit Interest Vs Consent 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.

Assessing Legitimate Interest vs Consent

Overview

GDPR Article 6(1) provides six lawful bases for processing. Consent (Article 6(1)(a)) and legitimate interest (Article 6(1)(f)) are the two most commonly used bases for commercial data processing. Choosing the wrong basis creates compliance risk: relying on consent when it cannot be freely given undermines validity, while relying on legitimate interest when consent is required (e.g., for electronic marketing under the ePrivacy Directive) violates sectoral law.

Decision Framework: When to Use Each Basis

Use Consent When:

  1. Regulatory requirement: Specific legislation mandates consent (e.g., ePrivacy Directive Article 5(3) for non-essential cookies, Article 13 for unsolicited electronic marketing)
  2. Special category data: Processing sensitive data under Article 9(2)(a) requires explicit consent
  3. Automated decision-making: Processing under Article 22(2)(c) requires explicit consent
  4. International transfers: Article 49(1)(a) explicit consent for transfers without adequacy/safeguards
  5. User control priority: The processing is entirely optional and the data subject should have full control

Use Legitimate Interest When:

  1. Power imbalance exists: Consent cannot be freely given (employer-employee, public authority-citizen)
  2. Processing is necessary: The processing is necessary for the controller's or third party's legitimate interest and is proportionate
  3. Reasonable expectation: The data subject would reasonably expect the processing (Recital 47)
  4. Withdrawal would be problematic: If consent withdrawal would cause operational issues (e.g., fraud prevention)
  5. No specific consent requirement: No ePrivacy or sectoral law mandates consent

Power Imbalance Indicators

Per EDPB Guidelines 05/2020 (paragraphs 13-25) and Recital 43, consent is presumed not to be freely given when a clear imbalance exists:

IndicatorExampleImplication
Employment relationshipEmployer asks employee to consent to monitoringUse LI or legal obligation, not consent
Public authorityTax authority processes taxpayer dataUse legal obligation or public task
Service dependencyOnly provider in market; user has no alternativeConsent may not be freely given
Contractual bundlingConsent required as condition of contract (Art. 7(4))Consent likely invalid
Vulnerable data subjectsChildren, elderly, patientsExtra scrutiny; consent may not be free
Significant consequenceRefusing consent leads to job loss or service terminationConsent not freely given

The Three-Part Legitimate Interest Assessment (LIA)

Per CJEU case law (C-13/16 Rigas, C-40/17 Fashion ID) and Article 29 Working Party Opinion 06/2014:

Part 1: Purpose Test

Is the interest legitimate?

  • The interest must be lawful (not in itself illegal)
  • The interest must be real and present (not speculative)
  • The interest must be sufficiently clearly articulated

CloudVault SaaS Inc. examples of legitimate interests:

  • Network and information security (Recital 49)
  • Fraud prevention and detection
  • Direct marketing to existing customers (Recital 47)
  • Internal administrative purposes within a group (Recital 48)
  • Service improvement based on aggregated usage analytics

Part 2: Necessity Test

Is the processing necessary for the legitimate interest?

  • Could the same interest be achieved with less data?
  • Could the same interest be achieved without processing personal data?
  • Is the processing proportionate to the interest pursued?

Part 3: Balancing Test

Do the data subject's rights and freedoms override the legitimate interest?

FactorWeighs Toward LIWeighs Toward Data Subject
Data sensitivityNon-sensitive dataSpecial category data
Reasonable expectationProcessing expected by data subjectSurprising or unexpected processing
RelationshipExisting customer/user relationshipNo prior relationship
ImpactMinimal impact on individualSignificant consequences
SafeguardsRobust safeguards in placeNo safeguards
Data subject controlEasy opt-out availableNo opt-out mechanism
Vulnerable groupsNo vulnerable individualsChildren or vulnerable adults
Data volumeMinimal data usedExtensive profiling

Decision Tree

START: Need to establish lawful basis for processing activity
  ├─► Q1: Does specific legislation require consent?
  │     (ePrivacy Art. 5(3) for cookies, Art. 13 for e-marketing,
  │      GDPR Art. 9(2)(a) for special categories, Art. 22(2)(c) for automated decisions)
  │     │
  │     ├─ YES → Use CONSENT (mandatory)
  │     │
  │     └─ NO → Continue to Q2
  ├─► Q2: Is there a power imbalance between controller and data subject?
  │     (employer-employee, public authority, service dependency)
  │     │
  │     ├─ YES → Consent likely INVALID; consider LEGITIMATE INTEREST
  │     │         (or legal obligation/public task if applicable)
  │     │
  │     └─ NO → Continue to Q3
  ├─► Q3: Is consent conditioned on the service?
  │     (Would refusing consent result in service denial or degradation?)
  │     │
  │     ├─ YES → Violates Art. 7(4); consent likely INVALID
  │     │         Consider LEGITIMATE INTEREST or restructure the service
  │     │
  │     └─ NO → Continue to Q4
  ├─► Q4: Is consent withdrawal operationally feasible?
  │     (Can you stop processing immediately if consent is withdrawn?)
  │     │
  │     ├─ NO → LEGITIMATE INTEREST may be more appropriate
  │     │        (e.g., fraud prevention cannot stop mid-transaction)
  │     │
  │     └─ YES → Continue to Q5
  ├─► Q5: Does the data subject reasonably expect this processing?
  │     │
  │     ├─ YES → Either CONSENT or LEGITIMATE INTEREST may work
  │     │         Choose based on control preference and overhead
  │     │
  │     └─ NO → CONSENT is more appropriate
  │               (unexpected processing needs explicit agreement)
  └─► Q6: Final determination
        ├─ If consent: Implement full Art. 7 requirements (freely given, specific,
        │   informed, unambiguous, withdrawal as easy as giving)
        └─ If LI: Document three-part LIA, implement opt-out mechanism,
            include in privacy notice per Art. 13(1)(d)/14(2)(b)

Common Scenarios at CloudVault SaaS Inc.

ScenarioRecommended BasisReasoning
Essential cookies for session managementNot consent; exempt under ePrivacy Art. 5(3)Strictly necessary; no consent required
Analytics cookies (non-essential)ConsentePrivacy Art. 5(3) requires consent for non-essential cookies
Email marketing to existing customersLegitimate interest (soft opt-in)ePrivacy Art. 13(2) allows soft opt-in for existing customers with opt-out
Email marketing to new contactsConsentePrivacy Art. 13(1) requires prior consent for unsolicited e-marketing
Fraud detection on transactionsLegitimate interestCannot withdraw; Recital 47 recognizes fraud prevention
Sharing data with Datalytics Partners Ltd.ConsentThird-party sharing not reasonably expected; user control appropriate
Network security monitoringLegitimate interestRecital 49 explicitly recognizes network security as LI
Employee performance monitoringLegitimate interestPower imbalance makes employee consent invalid (WP29 Opinion 2/2017)

Key Regulatory References

  • GDPR Article 6(1)(a) — Consent as lawful basis
  • GDPR Article 6(1)(f) — Legitimate interest as lawful basis
  • GDPR Article 7(4) — Conditionality prohibition
  • GDPR Recitals 47, 48, 49 — Guidance on legitimate interest scenarios
  • Article 29 WP Opinion 06/2014 on Legitimate Interest (WP217)
  • EDPB Guidelines 05/2020 on Consent — Power imbalance analysis
  • CJEU C-13/16 (Rigas) — Legitimate interest balancing test
  • CJEU C-40/17 (Fashion ID) — Joint controller LI responsibility
  • ePrivacy Directive Articles 5(3) and 13 — Sector-specific consent requirements
  • WP29 Opinion 2/2017 on Data Processing at Work — Employee consent limitations

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 Legit Interest Vs Consent AI skill do?

Decision framework for choosing between consent and legitimate interest as the lawful basis for processing. Covers power imbalance indicators, conditionality prohibition under Article 7(4), granularity requirements, the three-part LIA test (purpose, necessity, balancing), and practical decision trees for common scenarios.

Why use Legit Interest Vs Consent on TypingMind?

Because you install it once and use it with any model. Legit Interest Vs Consent 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 Legit Interest Vs Consent 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/legit-interest-vs-consent. 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 Legit Interest Vs Consent?

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 Legit Interest Vs Consent?

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

Is the Legit Interest Vs Consent 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 👇