external/anthropic-cybersecurity-skills/skills/conducting-gdpr-compliance-assessment/SKILL.md
Conduct comprehensive GDPR compliance assessments by evaluating data processing activities against EU Regulation 2016/679, including Article 30 records of processing, lawful basis validation, data subject rights implementation, Data Protection Impact Assessments (DPIAs) under Article 35, breach notification procedures, international transfer safeguards (SCCs, adequacy decisions), and technical/organizational measures under Article 32. Use when processing personal data of EU residents, preparing for supervisory authority audits, implementing privacy-by-design for new systems, scoping compliance gaps for M&A due diligence, assessing third-party processors, or responding to data subject access requests at scale. Incorporates 2026 guidance from ICO, EDPB, and post-Data (Use and Access) Act 2025 UK-GDPR considerations. Do not use for implementing specific Article 32 controls — use implementing-gdpr-data-protection-controls; or for DSAR automation — use implementing-gdpr-data-subject-access-request.
npx skillsauth add seikaikyo/dash-skills conducting-gdpr-compliance-assessmentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Effective Date: August 2026
Legal Basis: EU Regulation 2016/679 (GDPR), UK GDPR as amended by Data Protection Act 2018 and Data (Use and Access) Act 2025 (ukpga/2025/18)
Pending Changes: Digital Omnibus proposal (COM(2025) 837) would change Article 30(5) threshold from 250 to 750 employees and Article 33 breach notification from 72h to 96h. Still in proposal stage; current requirements remain in force.
Do not use for:
For detailed procedures, templates, and examples, see references/detailed-workflow.md
GDPR applies if:
Check: EU office? EU website targeting? Behavioral tracking?
Document for EACH activity:
Tools: Use scripts/article30_parser.py, article30_validator.py, generate_ropa_report.py
Common gaps: Missing retention periods (68%), vague purposes, undocumented transfers
| Basis | Use Case | Key Requirement | |-------|----------|-----------------| | Consent (6(1)(a)) | Marketing, profiling | Freely given, specific, withdrawable | | Contract (6(1)(b)) | Order fulfillment | Strictly necessary only | | Legal Obligation (6(1)(c)) | Tax records | Cite specific law | | Legitimate Interest (6(1)(f)) | Fraud prevention, analytics | Three-part test + balancing |
Action: Map each Article 30 activity to one lawful basis. Document legitimate interest assessments.
Verify capability for:
Test: Process sample DSAR through full workflow. Use scripts/ for automation.
DPIA mandatory for:
Template: See references/detailed-workflow.md for complete DPIA structure
Content: Description, necessity, risks, mitigation, consultation (DPO, supervisory authority if novel high-risk)
72-hour rule: Notify supervisory authority within 72 hours of becoming aware of breach likely to risk rights.
Decision tree:
Content: Nature, categories/numbers, DPO contact, consequences, mitigation
Mechanisms:
Post-Schrems II: Assess destination country surveillance laws, implement supplementary measures (encryption with EU-held keys)
"Security appropriate to the risk":
Pseudonymization vs. Anonymization: Pseudo = reversible (still personal data); Anon = irreversible (no longer GDPR)
Generate compliance report:
Format: See Output Format section below
| Term | Definition | |------|------------| | Controller | Determines purposes and means of processing (Article 4(7)) | | Processor | Processes on behalf of controller (Article 4(8); requires DPA per Article 28) | | Personal Data | Any information relating to identified/identifiable natural person (Article 4(1)) | | Special Categories | Health, biometric, genetic, racial, political, religious, trade union, sex life data (Article 9; heightened protection) | | Consent | Freely given, specific, informed, unambiguous indication of wishes (Article 4(11)) | | Legitimate Interest | Lawful basis requiring three-part test: purpose, necessity, balancing (Recital 47) | | DPIA | Data Protection Impact Assessment for high-risk processing (Article 35) | | DPO | Data Protection Officer (Article 37; mandatory for public authorities, large-scale monitoring/special categories) | | SCCs | Standard Contractual Clauses for international transfers (Commission Implementing Decision 2021/914) | | Supervisory Authority | National data protection regulator (ICO for UK, CNIL for France, BfDI for Germany) |
article30_parser.py, article30_validator.py (included)Context: Acquiring SaaS company with 50K EU customers. Need compliance assessment within 2 weeks.
Approach:
Context: ICO formal inquiry after consumer complaint about unsubscribe not working.
Response:
GDPR COMPLIANCE ASSESSMENT REPORT
===================================
Organization: XYZ Corp | Assessment Date: 2026-08-24
Assessor: Jane Smith, CIPP/E | DPO: [email protected]
EXECUTIVE SUMMARY
━━━━━━━━━━━━━━━━━
Overall Status: PARTIAL COMPLIANCE (67/100)
Critical Gaps: 3 | High: 5 | Medium: 8 | Low: 12
CRITICAL FINDINGS
━━━━━━━━━━━━━━━━━
1. Article 33: No breach notification procedures (72-hour deadline unmet)
2. Chapter V: International transfers to US without SCCs (Schrems II violation)
3. Article 30: Records incomplete (retention periods missing for 40% of activities)
ARTICLE-BY-ARTICLE STATUS
━━━━━━━━━━━━━━━━━━━━━━━━
✅ Article 3: Applicability confirmed (EU establishment)
⚠️ Article 6: Lawful basis documented but 3 activities use invalid bundled consent
✅ Article 15-23: DSAR procedures operational (18-day avg response time)
❌ Article 28: 40% of processors lack signed DPAs
⚠️ Article 32: Encryption at rest implemented but no MFA on admin accounts
❌ Article 33/34: No breach notification procedures
⚠️ Article 35: DPIA completed for profiling but not reviewed in 18 months
❌ Chapter V: US transfers without SCCs
REMEDIATION ROADMAP
━━━━━━━━━━━━━━━━━━━
Priority 1 (0-30 days, $50K):
- Implement breach notification procedures + incident register
- Execute SCCs with AWS, Stripe (Module 2)
- Complete Article 30 records (retention periods, security measures)
Priority 2 (1-3 months, $80K):
- Execute DPAs with remaining 8 processors
- Deploy MFA on all admin accounts
- Conduct legitimate interest assessments for analytics
Priority 3 (3-6 months, $40K):
- Review and update DPIA
- Automated DSAR response workflow
- Annual GDPR training for staff
COMPLIANCE SCORE: 67/100 → Target 90/100 (6 months post-remediation)
tools
Parse Windows forensic artifacts—$MFT/$J (MFTECmd), Prefetch (PECmd), registry hives (RECmd), shellbags, and Amcache—into normalized CSV/JSON with Eric Zimmerman's EZ Tools, then load results into Timeline Explorer for analysis. Use during DFIR/incident-response investigations, after triage collection (e.g. with KAPE), to establish program execution, file/folder access, and persistence evidence from acquired forensic images.
development
Build automated multi-turn adversarial attacks against conversational LLM targets using Microsoft PyRIT's RedTeamingOrchestrator, CrescendoOrchestrator (gradual escalation), and TreeOfAttacksWithPruningOrchestrator (adaptive branching), with scorer feedback loops and persisted conversation memory. Use when single-shot LLM scanning is insufficient and you need multi-turn, scorer-driven AI red-team campaigns against a chatbot or agent.
testing
Stand up MISP, enable and cache curated threat feeds (CIRCL, abuse.ch, Feodo Tracker), apply warninglists to suppress false positives, query indicators with PyMISP, and export attributes as auto-generated Suricata/Sigma/Wazuh detection rules. Use when maturing a MISP instance to actively drive detection, curating threat feeds with quality controls, or automating IOC-to-detection pipelines for the SIEM/IDS.
tools
Stand up a Sliver C2 server and mTLS listeners, generate cross-platform implants and beacons, and run post-exploitation, pivoting, and BOF/.NET tooling via the Armory for adversary emulation. Use during authorized, rules-of-engagement-bound red-team engagements that need a full open-source C2 lifecycle spanning server setup, implant generation, and post-exploitation tradecraft.