Guides compliance with South Korea's Personal Information Protection Act (PIPA, 개인정보 보호법).

Apache-2.0Auto-check passedLegal & Compliance

Install Korea Pipa

skills CLI
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill korea-pipa -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mukul975/Privacy-Data-Protection-Skills korea-pipa --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/privacy/korea-pipa .claude/skills/korea-pipa && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
korea-pipa
GitHub stars
301
Token cost
~3.2k tokens
SKILL.md length
1,428 words
Files
5 (incl. scripts, references, assets)
Skills in repo
280
Repo updated
First seen
Licence
Apache-2.0

At a glance

Guides compliance with South Korea's Personal Information Protection Act (PIPA, 개인정보 보호법).

  • Works in 3 steps: Statistical purposes → Scientific research (including… → Preservation of records in the public…
  • Tasks that involve Privacy and GDPR
  • SKILL.md covers Overview, Scope and Definitions, Consent Framework and Pseudonymisation Framework…, plus 5 more sections
  • Runs Python scripts from its folder

What it does

Korea Pipa is an agent skill from mukul975/Privacy-Data-Protection-Skills. Guides compliance with South Korea's Personal Information Protection Act (PIPA, 개인정보 보호법). Covers pseudonymisation framework, notification requirements, PIPC enforcement, consent standards, and cross-border transfer rules under the 2023 amendments. Keywords: PIPA, Korea data protection, PIPC, pseudonymisation, consent, cross-border transfers.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/template.md`, `references/standards.md` and `references/workflows.md`).

It sits in Legal & Compliance, covering Privacy and GDPR. The repository describes itself as: 282+ structured privacy & data protection skills for AI agents. GDPR, CCPA, EU AI Act, HIPAA, LGPD, PIPL, DPDP Act. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Privacy and GDPR

Example prompts

  • “Use the korea-pipa skill to guide compliance with South Korea's Personal Information Protection Act (PIPA, 개인정보 보호법)”
  • “/korea-pipa”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Statistical purposes
  2. Scientific research (including industrial research)
  3. Preservation of records in the public interest

What it can do on your machine

Read from SKILL.md and the folder at commit 9b2ef9e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Korea Pipa loads about 3.2k tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 1,428 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mukul975/Privacy-Data-Protection-Skills at commit 9b2ef9e, republished under its Apache-2.0 licence (© mukul975). 1,428 words, ~3,160 tokens.

Download SKILL.mdSave it as .claude/skills/korea-pipa/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
korea-pipa
description
Guides compliance with South Korea's Personal Information Protection Act (PIPA, 개인정보 보호법). Covers pseudonymisation framework, notification requirements, PIPC enforcement, consent standards, and cross-border transfer rules under the 2023 amendments. Keywords: PIPA, Korea data protection, PIPC, pseudonymisation, consent, cross-border transfers.
license
Apache-2.0
metadata.author
mukul975
metadata.version
1.0
metadata.domain
privacy
metadata.subdomain
global-privacy-regulations
metadata.tags
pipa, korea-data-protection, pipc, pseudonymisation, cross-border-transfers

South Korea PIPA Compliance

Overview

The Personal Information Protection Act (PIPA, 개인정보 보호법) is South Korea's comprehensive data protection law, originally enacted on 29 September 2011 (Act No. 10465) and significantly amended in 2020 (effective 5 August 2020) and 2023 (effective 15 September 2023). The Personal Information Protection Commission (PIPC, 개인정보보호위원회) is the independent supervisory authority with centralised enforcement jurisdiction since the 2020 amendments consolidated regulatory authority from multiple agencies.

South Korea received an adequacy decision from the European Commission on 17 December 2021, recognising PIPA as providing an adequate level of data protection for GDPR transfer purposes.

Scope and Definitions

Personal Information (Art. 2(1))

Information relating to a living individual that identifies or can identify the individual through the information alone or in combination with other information that can be easily used. Includes:

  • Name, resident registration number, image
  • Information that individually does not identify but can identify when combined with other easily accessible information
Pseudonymised Information (Art. 2(1-2), introduced 2020)

Personal information processed by partially deleting or replacing to make it impossible to identify a specific individual without the use of additional information. Pseudonymised information may be processed for statistical purposes, scientific research, and preservation of records in the public interest without consent (Art. 28-2).

Sensitive Information (Art. 23)
  • Ideology, beliefs, membership of trade unions or political parties
  • Political opinions, health information, sex life
  • Genetic information, criminal record information
  • Biometric information used for identification
  • Race and ethnic origin (added by 2023 amendments)
RequirementPIPA ProvisionDetail
Informed consentArt. 15(2)Must disclose: purpose, items collected, retention period, right to refuse and consequences
Separate consentArt. 22(1)Consent for processing beyond the purpose must be separated from other consent items
Clear distinctionArt. 22(1)Important content must be clearly displayed (larger font, colour, bold)
Opt-in for marketingArt. 22(2)Marketing purpose collection requires separate opt-in consent
Refusal rightArt. 22(5)Data handler must not refuse service due to refusal of consent for non-essential information
Minor consentArt. 22(6)For children under 14, consent from legal representative required

Processing sensitive information requires the data subject's separate explicit consent or a specific legal basis. The consent must clearly indicate the sensitive categories being processed.

The 2023 amendments introduced additional lawful processing bases beyond consent:

BasisArticleDescription
ConsentArt. 15(1)(1)Data subject's consent obtained per Art. 22
Legal obligationArt. 15(1)(2)Special provisions in laws or compliance with legal obligations
Public institution dutyArt. 15(1)(3)Necessary for public institutions to perform statutory duties
Contract performanceArt. 15(1)(4)Necessary for contract with data subject
Legitimate interestArt. 15(1)(6)Necessary for legitimate interest of the data handler, where substantially related to the purpose and within the data subject's reasonable expectations (added 2023)
Urgent necessityArt. 15(1)(5)Urgently necessary for life, body, or property of the data subject or third party

Legitimate interest (Art. 15(1)(6)) requirements:

  • Reasonably related to the interest of the data handler
  • Substantially related to the original collection purpose
  • Within the reasonable expectations of the data subject
  • Data handler must document the legitimate interest assessment
  • The PIPC may issue further guidance on the scope and application

Pseudonymisation Framework (Arts. 28-2 to 28-7)

Permitted Uses of Pseudonymised Information (Art. 28-2)

Pseudonymised information may be processed without consent for:

  1. Statistical purposes
  2. Scientific research (including industrial research)
  3. Preservation of records in the public interest
Combination of Pseudonymised Information (Art. 28-3)
  • Combination of pseudonymised information held by different data handlers must be performed by an entity designated by the PIPC
  • The designated entity must apply additional pseudonymisation or anonymisation before providing the combined data to the requesting handler
  • The combination must receive prior PIPC approval
Safety Measures for Pseudonymised Information (Art. 28-4)
MeasureRequirement
Separation of additional informationAdditional information enabling re-identification must be stored and managed separately
Technical safeguardsEncryption or equivalent protection for additional information
Access restrictionsDesignation of authorised personnel; access logging
Prohibition on re-identificationProhibited from using pseudonymised information to re-identify individuals; if re-identification occurs accidentally, immediate destruction or cessation of processing required
Zenith Global Enterprises Pseudonymisation Register
Data SetPurposePseudonymisation MethodAdditional Information StoragePIPC Compliance
Customer shipping patternsStatistical analysis of route optimisationk-anonymity (k=5) with generalisation of location dataKey mapping table stored in HSM, separate from analytics environmentCompliant
Employee performance metricsIndustrial research on workforce productivityTokenisation of employee identifiersToken-identifier mapping in isolated database with MFA accessCompliant
Logistics volume trendsPublic interest statistical reportingAggregation to postal code level with suppression of groups < 10No additional information retained (anonymised output)Not applicable (anonymised)

Cross-Border Transfer Rules

Transfer Mechanisms (Art. 28-8, as amended 2023)

The 2023 amendments significantly reformed cross-border transfer provisions:

MechanismArticleDetail
ConsentArt. 28-8(1)(1)Data subject's consent with disclosure of: recipient, destination country, transfer purpose, PI items, right to refuse and consequences
Contract necessityArt. 28-8(1)(2)Transfer necessary for contract with data subject
Adequacy recognitionArt. 28-8(1)(3)Transfer to a country or international organisation recognised by the PIPC as having adequate protection
Standard contractual clausesArt. 28-8(1)(4)PIPC-approved standard contractual clauses between the parties
BCR equivalentArt. 28-8(1)(4)PIPC-approved data protection rules within a corporate group
PIPC certificationArt. 28-8(1)(5)Recipient certified by a PIPC-designated certification body
Show full SKILL.md (552 more words)Show less
PIPC Adequacy Recognitions

As of March 2026, the PIPC has recognised:

  • European Union / EEA (reciprocal with EU adequacy decision of December 2021)
  • United Kingdom (recognised 2022)
Notification Requirements for Cross-Border Transfer (Art. 28-8(3))

The data handler must notify the data subject of:

  • The recipient's identity
  • The destination country
  • The items of personal information transferred
  • The purpose of transfer
  • The retention and use period
  • The right to refuse and consequences of refusal

Zenith Global Enterprises Cross-Border Transfer Register:

Transfer IDFlowDestinationMechanismNotificationStatus
CBT-KR-001Customer data → EU HQGermany (EU)Adequacy recognitionPrivacy notice updatedActive
CBT-KR-002Employee data → Regional HRSingaporeStandard contractual clausesEmployee notice providedActive
CBT-KR-003Logistics data → APAC opsJapanConsent (Art. 28-8(1)(1))Consent collectedActive
CBT-KR-004Payment data → TreasuryUnited KingdomAdequacy recognitionPrivacy notice updatedActive

PIPC Enforcement

Administrative Penalties
Sanction TypePIPA ProvisionDetail
Corrective ordersArt. 64Orders to cease violations, take corrective measures, or implement safeguards
Administrative fines (과태료)Art. 75Up to KRW 50 million for procedural violations
Penalty surcharges (과징금)Art. 64-2Up to 3% of related revenue (increased from prior cap by 2023 amendments)
Criminal penaltiesArt. 71-73Imprisonment up to 5 years or fine up to KRW 50 million for serious violations
Public namingArt. 64(4)Public disclosure of violators
Notable PIPC Enforcement Actions

Meta Platforms (September 2022):

  • Fine: KRW 30.8 billion (approximately USD 22 million)
  • Violations: Collecting and using sensitive information (political views, sexual orientation, religious beliefs) without proper consent from approximately 3.3 million Korean Facebook users
  • Significance: Demonstrated PIPC willingness to impose significant fines on global technology companies

Kakao (2023):

  • Fine: KRW 15.1 billion
  • Violations: Collection and use of personal information beyond consented purposes in advertising services
  • Significance: Largest enforcement action against a domestic technology company

Scatter Lab (2021):

  • Fine: KRW 103 million
  • Violations: AI chatbot (Lee Luda) trained on personal conversations without consent
  • Significance: Established PIPC precedent for AI training data compliance under PIPA

Data Subject Rights

RightArticleResponse DeadlineImplementation
Right to accessArt. 3510 daysSelf-service portal in Korean
Right to correction/deletionArt. 3610 daysCorrection through customer portal; deletion workflow with legal hold check
Right to suspensionArt. 3710 daysProcessing suspension within 10 days of request
Right to notificationArt. 34Without delayBreach notification to affected individuals
Right to data portabilityArt. 35-2 (2023)Per PIPC regulationStructured export (implementation timeline per PIPC guidance)
Right regarding automated decisionsArt. 37-2 (2023)Per PIPC regulationRight to explanation and refusal of automated decisions

Breach Notification (Art. 34)

ElementRequirement
Individual notificationWithout delay upon discovery of breach
PIPC notificationWithin 72 hours of discovery for breaches affecting 1,000+ individuals
ContentFacts of breach, items of PI leaked, countermeasures, grievance procedures
Large-scale breach10,000+ individuals: additional reporting to PIPC and public notification through the website
Investigation cooperationCooperate fully with PIPC investigation

Compliance Programme

ComponentDetail
Internal management planDocumented plan per Art. 29 and Enforcement Decree Art. 30
Chief Privacy Officer (CPO)Designated officer meeting PIPA qualifications (Art. 31)
Annual trainingPIPA compliance training for all Korean employees
Technical safeguardsEncryption of resident registration numbers and sensitive data (Art. 24-2)
Data destructionDestruction within 5 days of retention period expiry (Art. 21)
Privacy impact assessmentRequired for public institutions; recommended for private sector for large-scale processing

© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references, assets) in skills/privacy/korea-pipa of mukul975/Privacy-Data-Protection-Skills.

  • SKILL.md
  • assets/template.md
  • references/standards.md
  • references/workflows.md
  • scripts/process.py

Open the folder on GitHubat commit 9b2ef9e

Compare with similar skills

Korea Pipa next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Korea Pipa compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Korea Pipa this skillmukul975/Privacy-Data-Protection-Skills301—~3.2kAutomated safety check: PassApache-2.0
C15tc15t/c15t1.9k1 repos~1.6kAutomated safety check: PassApache-2.0
HIPAA Safe Harbor Coverage Auditmaziyarpanahi/openmed5.5k—~1.7kAutomated safety check: PassApache-2.0
Korean Privacy Termskimlawtech/korean-privacy-terms587—~2.9kAutomated safety check: PassApache-2.0
Gdpr ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance9461 repos~3.9kAutomated safety check: PassMIT
Hipaa ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance9461 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • C15t

    c15t/c15t

    Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.

    1.9k GitHub starsUsed in 1 repo~1.6k tokens
    Legal & ComplianceAuto-check passed
  • Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.

    5.5k GitHub stars~1.7k tokensUpdated today
    Legal & ComplianceAuto-check passed
  • Korean Privacy Terms

    kimlawtech/korean-privacy-terms

    처리방침·이용약관 자동 생성 스킬 패키지 (v4.0). An agent skill from kimlawtech/korean-privacy-terms.

    587 GitHub stars~2.9k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Gdpr Compliance

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert GDPR compliance assistant covering all four core workflows: (1) auditing code and systems for GDPR violations, (2) drafting GDPR-compliant documents such as privacy policies, Data Processing…

    946 GitHub starsUsed in 1 repo~3.9k tokens
    Legal & ComplianceAuto-check passed
  • Hipaa Compliance

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert HIPAA compliance assistant for healthcare and software contexts.

    946 GitHub starsUsed in 1 repo~2.3k tokens
    Legal & ComplianceAuto-check passed
  • Pii Contract Analyze

    gregmos/PII-Shield

    Universal legal document processor with PII anonymization. An agent skill from gregmos/PII-Shield.

    150 GitHub stars~8.9k tokensUpdated 3 mo ago
    Legal & ComplianceAuto-check: notes

More from mukul975/Privacy-Data-Protection-Skills

All 280 skills in this repo
  • Age Gating Services

    mukul975/Privacy-Data-Protection-Skills

    Implements age-gating mechanisms for online services to restrict access based on user age.

    301 GitHub stars~3.7k tokensUpdated 6 mo ago
    Auto-check passed
  • AI Data Retention

    mukul975/Privacy-Data-Protection-Skills

    Manages AI model retention and machine unlearning requirements.

    301 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed
  • AI Dpia

    mukul975/Privacy-Data-Protection-Skills

    Conducts Data Protection Impact Assessments for AI and ML systems per EDPB Guidelines 04/2025 on AI processing.

    301 GitHub stars~3.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Dpia Mitigation Plan

    mukul975/Privacy-Data-Protection-Skills

    Structures risk mitigation planning and residual risk tracking for Data Protection Impact Assessments under GDPR Article 35(7)(d).

    301 GitHub stars~846 tokensUpdated 6 mo ago
    Auto-check passed
  • Gdpr Accountability

    mukul975/Privacy-Data-Protection-Skills

    Guides implementation of the GDPR accountability principle under Articles 5(2) and 24, including documentation requirements for policies, DPIAs, RoPA, training records, and breach logs.

    301 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed
  • Pia Threshold Screening

    mukul975/Privacy-Data-Protection-Skills

    Conducts pre-DPIA threshold screening to determine whether a full Data Protection Impact Assessment is required under GDPR Article 35.

    301 GitHub stars~880 tokensUpdated 6 mo ago
    Auto-check passed

Questions about Korea Pipa

What does Korea Pipa do?

Guides compliance with South Korea's Personal Information Protection Act (PIPA, 개인정보 보호법). Korea Pipa is an agent skill from mukul975/Privacy-Data-Protection-Skills. Guides compliance with South Korea's Personal Information Protection Act (PIPA, 개인정보 보호법).

When should I use Korea Pipa?

Korea Pipa fits situations like: tasks that involve Privacy and GDPR.

How do I install Korea Pipa in Claude Code?

Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill korea-pipa -a claude-code`. Or copy the skill folder (skills/privacy/korea-pipa in mukul975/Privacy-Data-Protection-Skills) into .claude/skills/korea-pipa in your project. Claude Code loads it when a task matches its description.

How do I install Korea Pipa in Codex?

Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill korea-pipa -a codex`. Or copy the skill folder (skills/privacy/korea-pipa in mukul975/Privacy-Data-Protection-Skills) into .agents/skills/korea-pipa in your project. Codex loads it when a task matches its description.

Can I use Korea Pipa in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill korea-pipa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/korea-pipa, .gemini/skills/korea-pipa, .github/skills/korea-pipa and .opencode/skills/korea-pipa in your project.

What does Korea Pipa need to run?

Going by SKILL.md and its folder, Korea Pipa needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Korea Pipa access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Korea Pipa safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Korea Pipa use?

Korea Pipa is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Korea Pipa use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Korea Pipa?

Skills that share tags, products or a category with Korea Pipa: C15t (c15t/c15t, 1.9k stars), HIPAA Safe Harbor Coverage Audit (maziyarpanahi/openmed, 5.5k stars), Korean Privacy Terms (kimlawtech/korean-privacy-terms, 587 stars) and Gdpr Compliance (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 946 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Korea Pipa?

mukul975 (a GitHub user) maintains it in mukul975/Privacy-Data-Protection-Skills, which has 301 GitHub stars. The repository holds 280 skills in this directory. The repository was last updated on March 16, 2026.

Source: mukul975/Privacy-Data-Protection-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.