Agent skill

Pia Vendor Processing

by mukul975 in mukul975/Privacy-Data-Protection-Skills

Conducts Privacy Impact Assessment for vendor and third-party data processing arrangements.

Apache-2.0Auto-check passedLegal & Compliance

Install Pia Vendor Processing

skills CLI
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill pia-vendor-processing -a claude-code

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

GitHub CLI
$ gh skill install mukul975/Privacy-Data-Protection-Skills pia-vendor-processing --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/pia-vendor-processing .claude/skills/pia-vendor-processing && 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
pia-vendor-processing
GitHub stars
295
Token cost
~2k tokens
SKILL.md length
911 words
Files
5 (incl. scripts, references, assets)
Skills in repo
278
Repo updated
First seen
Licence
Apache-2.0

At a glance

Conducts Privacy Impact Assessment for vendor and third-party data processing arrangements.

  • Works in 5 steps: Vendor Inventory and Classification… → Due Diligence Assessment (Week 2) → Data Processing Agreement Review (Week 3) → …
  • Tasks that involve Privacy and GDPR
  • SKILL.md covers Overview, Regulatory Framework, Vendor Risk Categories and PIA Methodology for Vendor…, plus 1 more section
  • Runs Python scripts from its folder

What it does

Pia Vendor Processing is an agent skill from mukul975/Privacy-Data-Protection-Skills. Conducts Privacy Impact Assessment for vendor and third-party data processing arrangements. Covers processor due diligence, Data Processing Agreement (DPA) requirements under GDPR Article 28, sub-processor management, cross-border vendor transfers, cloud service provider assessments, and ongoing vendor monitoring. Keywords: vendor PIA, processor assessment, DPA, Article 28, sub-processor, cloud privacy, third-party risk.

Its SKILL.md is about 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 and Fundraising and pitch decks. 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
  • Tasks that involve Fundraising and pitch decks

Example prompts

  • “Use the pia-vendor-processing skill to conduct Privacy Impact Assessment for vendor and third-party data processing arrangements”
  • “/pia-vendor-processing”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Vendor Inventory and Classification (Week 1)
  2. Due Diligence Assessment (Week 2)
  3. Data Processing Agreement Review (Week 3)
  4. Risk Assessment and Mitigation (Week 4)
  5. Ongoing Monitoring Framework (Week 5)

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

Pia Vendor Processing loads about 2k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 911 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.7k

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). 911 words, ~1,969 tokens.

Download SKILL.mdSave it as .claude/skills/pia-vendor-processing/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
pia-vendor-processing
description
Conducts Privacy Impact Assessment for vendor and third-party data processing arrangements. Covers processor due diligence, Data Processing Agreement (DPA) requirements under GDPR Article 28, sub-processor management, cross-border vendor transfers, cloud service provider assessments, and ongoing vendor monitoring. Keywords: vendor PIA, processor assessment, DPA, Article 28, sub-processor, cloud privacy, third-party risk.
license
Apache-2.0
metadata.author
mukul975
metadata.version
1.0
metadata.domain
privacy
metadata.subdomain
privacy-impact-assessment
metadata.tags
vendor-pia, processor-assessment, dpa, article-28, sub-processor, cloud-privacy

Privacy Impact Assessment for Vendor Processing

Overview

When a controller engages a processor (vendor) to process personal data on its behalf, GDPR Article 28 imposes specific obligations on the controller to ensure that the processor provides sufficient guarantees to implement appropriate technical and organisational measures. The EDPB has repeatedly emphasized that the controller remains accountable for the processing regardless of delegation to a vendor. This skill provides a structured PIA methodology for assessing and managing the privacy risks of vendor data processing arrangements.

Regulatory Framework

GDPR Article 28 — Processor Obligations
RequirementDescription
Art. 28(1)Controller shall use only processors providing sufficient guarantees
Art. 28(2)Processor shall not engage another processor (sub-processor) without prior specific or general written authorisation
Art. 28(3)Processing governed by a contract or legal act setting out subject matter, duration, nature, purpose, data types, categories of data subjects, and controller obligations/rights
Art. 28(3)(a)-(h)Mandatory DPA clauses: process only on documented instructions, confidentiality, security measures, sub-processor conditions, assist with data subject rights, assist with security/breach/DPIA, delete or return data, provide audit information
Art. 28(4)Sub-processor must be bound by the same data protection obligations
Art. 28(5)Adherence to approved codes of conduct or certification (Art. 42) as elements to demonstrate sufficient guarantees
Processor Selection Criteria (EDPB Guidance)

The controller must assess the processor's:

  • Technical expertise and security measures
  • Track record and reputation (including enforcement history)
  • Ability to ensure data subject rights can be exercised
  • Data location and cross-border transfer implications
  • Sub-processor chain management capability
  • Business continuity and data recovery capability
  • Willingness to submit to audits

Vendor Risk Categories

Risk CategoryExamplesRisk Level
Cloud infrastructure (IaaS/PaaS)AWS, Azure, GCP — hosting personal dataHigh (data at rest and in transit under vendor control)
SaaS applicationsCRM, HRIS, email marketing — processing personal data in vendor applicationHigh (vendor application logic and access controls)
Analytics providersWebsite analytics, marketing attribution — processing behavioural dataMedium-High (data sharing, profiling, cookie compliance)
IT support / managed servicesHelpdesk, system administration — access to personal data during supportMedium (access-based risk, not purpose-based)
Payment processorsCard processing, billing — financial personal dataHigh (PCI DSS intersection, financial data sensitivity)
Sub-processorsVendor's own vendors processing controller's dataHigh (reduced visibility and control)

PIA Methodology for Vendor Processing

Phase 1: Vendor Inventory and Classification (Week 1)
  1. Inventory all vendors processing personal data on behalf of the organisation.
  2. For each vendor, document: personal data categories processed, data subject categories, processing purposes, data volumes, data locations.
  3. Classify each vendor by risk category based on data sensitivity, processing scope, and access level.
  4. Identify the vendor's sub-processors and their roles.
  5. Determine cross-border transfer implications for each vendor.
Phase 2: Due Diligence Assessment (Week 2)
  1. Request and review the vendor's security certifications (ISO 27001, SOC 2, CSA STAR).
  2. Review the vendor's privacy certifications and GDPR compliance evidence (ISO 27701, APEC CBPR).
  3. Check the vendor's enforcement history with supervisory authorities.
  4. Assess the vendor's technical and organisational security measures against the controller's requirements.
  5. Evaluate the vendor's data breach notification capability and track record.
  6. Review the vendor's sub-processor management process.
  7. Assess the vendor's ability to assist with data subject rights requests.
Show full SKILL.md (386 more words)Show less
Phase 3: Data Processing Agreement Review (Week 3)
  1. Verify the DPA covers all Art. 28(3) mandatory provisions.
  2. Check that processing instructions are specific and documented (not generic catch-all clauses).
  3. Verify sub-processor authorisation mechanism: specific or general with notification and objection rights.
  4. Ensure data deletion or return obligations at contract termination are clear and enforceable.
  5. Verify audit rights: right to conduct or commission audits of the processor.
  6. Check cross-border transfer mechanisms (SCCs, BCRs, adequacy) for international vendors.
  7. Assess liability and indemnification provisions for data protection breaches.
Phase 4: Risk Assessment and Mitigation (Week 4)
  1. For each vendor, assess the risk to data subjects from the vendor's processing.
  2. Consider: data breach at vendor, unauthorised access by vendor employees, sub-processor chain risk, vendor lock-in, business continuity failure.
  3. Score risks on likelihood and severity matrix.
  4. Identify mitigation measures: encryption (controller-managed keys), pseudonymisation before transfer to vendor, access restrictions, monitoring, contractual controls.
  5. Assess residual risk after mitigation.
Phase 5: Ongoing Monitoring Framework (Week 5)
  1. Define vendor review frequency based on risk classification (high-risk: annual; medium: biennial).
  2. Establish vendor security questionnaire process for periodic reassessment.
  3. Monitor vendor sub-processor changes (notification process, assessment of new sub-processors).
  4. Track vendor incidents and breach notifications.
  5. Conduct or commission periodic audits for high-risk vendors.
  6. Define vendor exit strategy: data return, deletion verification, transition plan.

Enforcement Precedents

  • CJEU Wirtschaftsakademie (C-210/16, 2018): Facebook fan page administrator held to be joint controller with Facebook; controllers cannot avoid responsibility by using a vendor platform.
  • CJEU Fashion ID (C-40/17, 2019): Website operator embedding Facebook Like button held to be joint controller for the collection and transmission of data; responsibility for vendor components on own website.
  • Belgian DPA vs IAB Europe (2022): EUR 250,000 fine; TCF framework operator held to be controller, not processor; demonstrates that contractual designation does not determine controller/processor status.
  • Spanish AEPD vs Vodafone (2021): EUR 8.15 million fine for failure to adequately manage processors and sub-processors handling customer data; insufficient DPA controls.
  • Finnish DPA vs Posti Group (2020): EUR 100,000 fine for inadequate processor management; controller failed to verify processor's compliance with data processing instructions.
  • Dutch DPA guidance on cloud services (2022): Detailed assessment methodology for cloud vendor privacy compliance, including requirement to conduct DPIA for cloud migrations involving personal data.

© 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/pia-vendor-processing 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

Pia Vendor Processing 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.

Pia Vendor Processing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pia Vendor Processing this skillmukul975/Privacy-Data-Protection-Skills295—~2kAutomated safety check: PassApache-2.0
General Counsel Advisoralirezarezvani/claude-skills28k—~2.3kAutomated safety check: PassMIT
TprmSushegaad/Claude-Skills-Governance-Risk-and-Compliance942—~2.3kAutomated safety check: PassMIT
Cross Regulatory Impact Analyzer Patrick Munrolawve-ai/awesome-legal-skills836—~3.1kAutomated safety check: PassAGPL-3.0
Vendor Due Diligence Patrick Munrolawve-ai/awesome-legal-skills836—~4.1kAutomated safety check: PassAGPL-3.0
Preparing Launch AssetsGTM-Strategist/gtm-strategist-skills261—~5kAutomated safety check: PassMIT

Similar skills

  • General Counsel Advisor

    alirezarezvani/claude-skills

    General Counsel advisory for startups: contract review (MSA, SaaS, NDA, DPA, employment), IP strategy, term sheet decoding, and regulatory landscape mapping.

    28k GitHub stars~2.3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Tprm

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

    Expert third-party risk management (TPRM) advisor — a vendor risk analyst for the full lifecycle: risk-based vendor tiering, tailored due-diligence questionnaires (SIG-style or mapped to ISO 27001…

    942 GitHub stars~2.3k tokensUpdated 4 days ago
    Legal & ComplianceAuto-check passed
  • Analyzes how multiple regulations interact for a specific product, service, or business model.

    836 GitHub stars~3.1k tokensUpdated 6 days ago
    Legal & ComplianceAuto-check passed
  • Vendor Due Diligence Patrick Munro

    lawve-ai/awesome-legal-skills

    Risk-based vendor assessment framework for IT service providers, technology vendors, and third-party partners under DORA, NIS2, GDPR.

    836 GitHub stars~4.1k tokensUpdated 6 days ago
    Legal & ComplianceAuto-check passed
  • Preparing Launch Assets

    GTM-Strategist/gtm-strategist-skills

    A skill your agent uses when the user needs to build launch assets like a website, pitch deck, press release, product demo, or media kit.

    261 GitHub stars~5k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Privacy Data Security

    JoelLewis/finance_skills

    Design and operate privacy and data security programs for SEC-registered firms under Reg S-P, Reg S-ID, and SEC cybersecurity expectations.

    205 GitHub stars~11k tokensUpdated 2 mo ago
    EducationAuto-check passed

More from mukul975/Privacy-Data-Protection-Skills

All 278 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.

    295 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.

    295 GitHub stars~1.9k 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).

    295 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.

    295 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.

    295 GitHub stars~880 tokensUpdated 6 mo ago
    Auto-check passed
  • Retention Schedule

    mukul975/Privacy-Data-Protection-Skills

    Designs and implements data retention schedules compliant with GDPR Article 5(1)(e) storage limitation principle.

    295 GitHub stars~3.3k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Pia Vendor Processing

What does Pia Vendor Processing do?

Conducts Privacy Impact Assessment for vendor and third-party data processing arrangements. Pia Vendor Processing is an agent skill from mukul975/Privacy-Data-Protection-Skills. Conducts Privacy Impact Assessment for vendor and third-party data processing arrangements.

When should I use Pia Vendor Processing?

Pia Vendor Processing fits situations like: tasks that involve Privacy and GDPR; tasks that involve Fundraising and pitch decks.

How do I install Pia Vendor Processing in Claude Code?

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

How do I install Pia Vendor Processing in Codex?

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

Can I use Pia Vendor Processing 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 pia-vendor-processing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pia-vendor-processing, .gemini/skills/pia-vendor-processing, .github/skills/pia-vendor-processing and .opencode/skills/pia-vendor-processing in your project.

What does Pia Vendor Processing need to run?

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

Does Pia Vendor Processing 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 Pia Vendor Processing 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 Pia Vendor Processing use?

Pia Vendor Processing 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 Pia Vendor Processing use?

About 2k tokens (SKILL.md is roughly 7.9k 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 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Pia Vendor Processing?

Skills that share tags, products or a category with Pia Vendor Processing: General Counsel Advisor (alirezarezvani/claude-skills, 28k stars), Tprm (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 942 stars), Cross Regulatory Impact Analyzer Patrick Munro (lawve-ai/awesome-legal-skills, 836 stars) and Vendor Due Diligence Patrick Munro (lawve-ai/awesome-legal-skills, 836 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pia Vendor Processing?

mukul975 (a GitHub user) maintains it in mukul975/Privacy-Data-Protection-Skills, which has 295 GitHub stars. The repository holds 278 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.