AI-agent skill · Claude Code · Codex · Cursor · Gemini CLI
GDPR Privacy Scanner lets your AI coding agent check datasets (CSV, Excel, JSON, Parquet, SQLite, logs) and code for personal data before you build AI or analytics on them. It finds names, e-mails, phones, addresses, IBANs, payment cards and 16 EU and UK national ID numbers (checking their check digits), special-category data such as health or religion, and how many people could be re-identified from ordinary columns like birth date and postcode. Then it plans and applies pseudonymisation on a copy, re-checks the result and writes a short GDPR report.
I froze the skill, then asked a fresh AI agent that had never seen its code to build a realistic test set from scratch: 20 tables, 280 columns in 16 languages (Italian, German, Dutch, Spanish, French, Polish, Portuguese, English, Czech, Romanian, Swedish, Greek, Hungarian, Estonian, Bulgarian, Slovak), as CSV, TSV, JSON, JSONL, Excel, SQLite and a log file. Every column has a correct label, and 116 of the 280 are look-alikes that are not personal data (business contact details, order and booking numbers, product codes, timestamps, aggregates). Version 1.1.0 was scored once, with no changes afterwards.
| Kind of data | Found |
|---|---|
| E-mails, phones, IBANs, cards, IPs | 22 / 23 |
| National ID numbers | 13 / 13 |
| Names | 17 / 22 |
| IDs that link a row to a person | 9 / 17 |
| Quasi-identifiers (birth date, age, postcode, ...) | 51 / 62 |
| Special categories (Art. 9) and criminal data | 10 / 19 |
| Free text containing personal data | 8 / 8 |
| Table | Column | Truth | Scanner |
|---|---|---|---|
| abbonati_mobile_2026.csv | rif_disp | device_id | not found |
| slimme_meter_metingen.jsonl | gateway.ip | ip_address | not found |
| reservations_hotels.json | client.nom | person_name | not found |
| gabinet_stomatologiczny.xlsx::Pacjenci | data_ur | date_of_birth | not found |
| gabinet_stomatologiczny.xlsx::Pacjenci | procedura | health | not found |
| gabinet_stomatologiczny.xlsx::Pacjenci | lekarz | person_name | not found |
| gabinet_stomatologiczny.xlsx::Pacjenci | field_7 | health | not found |
| farmacia_cartao_cliente.csv | n_cartao | customer_id | not found |
| farmacia_cartao_cliente.csv | medicamento_receitado | health | not found |
| loket_aanvragen.tsv | nummerplaat | vehicle_plate | not found |
| loket_aanvragen.tsv | behandelaar | customer_id | not found |
| prijimaci_rizeni_2026.csv | datum_narozeni | date_of_birth | not found |
| prijimaci_rizeni_2026.csv | specialni_potreby | health | not found |
| candidates_pipeline.csv | current_title | occupation | not found |
| candidates_pipeline.csv | garda_vetting | criminal | not found |
| dosare_daune_auto.csv | leziuni | health | not found |
| kyc_privatkunder.csv | kundnr | customer_id | not found |
| kyc_privatkunder.csv | adress | postal_address | not found |
| kyc_privatkunder.csv | postnr | postal_code | not found |
| paraggelies_delivery.csv | πελάτης | person_name | not found |
| paraggelies_delivery.csv | διεύθυνση_παράδοσης | postal_address | not found |
| paraggelies_delivery.csv | ΤΚ | postal_code | not found |
| paraggelies_delivery.csv | τηλ_καταστήματος | not personal | phone |
| paraggelies_delivery.csv | διανομέας_id | customer_id | not found |
| elearning_beiratkozasok.csv | felhasznalonev | customer_id | not found |
| elearning_beiratkozasok.csv | kor | age | not found |
| elearning_beiratkozasok.csv | munkamenet_id | device_id | not found |
| elearning_beiratkozasok.csv | tamogatas_email | not personal | |
| biopank_proovid.tsv | nimi | person_name | not found |
| biopank_proovid.tsv | sugu | gender | not found |
| biopank_proovid.tsv | APOE_genotüüp | genetic | not found |
| hr_baltic.db::employees | sick_days_ytd | health | not found |
| hr_baltic.db::payslips | pay_date | not personal | income |
| anketa_naselenie_2026.csv | id_респондент | customer_id | not found |
| anketa_naselenie_2026.csv | населено_място | city | not found |
| anketa_naselenie_2026.csv | сексуална_ориентация | sex_life_orientation | not found |
| faktury_dodavatelov.csv | iban_dodavatela | not personal | iban |
| faktury_dodavatelov.csv | sidlo_ulica | not personal | postal_address |
| faktury_dodavatelov.csv | mesto | not personal | city |
| faktury_dodavatelov.csv | psc | not personal | postal_code |
| faktury_dodavatelov.csv | kontakt_email | not personal | |
| faktury_dodavatelov.csv | kontaktna_osoba | person_name | not found |
History, for honesty: an earlier blind test (18 tables, 256 columns, built the same way) found 94 of 139
with version 1.0.0 and 96 of 139 with 1.0.1, with 15 false alarms out of 117.
It was weak on ID columns like KundenNr and on languages it did not know (Greek, Czech, Hungarian). I added 22 EU languages and
person-ID rules, then built the new blind test above to measure the new version fairly.
9 well-known datasets (Chinook (SQLite), Northwind (SQLite), Sakila (SQLite), Titanic (titanic3.csv), UCI Adult census, Cleveland heart disease, US medical insurance, IBM Telco churn, UCI red wine (negative control)): 325 columns. I wrote the correct answer for every column before the first run.
| Version | Personal columns found | False alarms |
|---|---|---|
| 1.0.0 (frozen, first run) | 78 / 111 | 28 / 214 |
| 1.1 (after fixes; not blind) | 93 / 111 | 5 / 214 |
What it still misses here: abbreviated medical columns in the heart-disease data (Fbs, Thal, Oldpeak...)
and US state columns. After pseudonymising with the default plan, records unique on ordinary attributes in the census data fell from
57% to 1.3%. Small tables (8 employees) stay unique: the report says so and suggests dropping them.
It also reads code for privacy problems: personal data in logs, sent to LLM APIs or trackers, plain hashes of e-mails, special-category fields in schemas, personal data saved in notebook outputs. On 3 real open-source projects (miguelgrinberg/microblog, fastapi/full-stack-fastapi-template, mckaywrigley/chatbot-ui) the first version raised 7 findings, of which 1 was real: microblog app/models.py:141 MD5 of the user's e-mail sent to Gravatar (unkeyed hash, PRV006). After fixing the noise it raises 1, the real one.
EU companies and teams that want to train AI, run analytics or share data built from customer, patient or employee records.
One Python package, standard library only (Python 3.10+; pandas only for Excel/Parquet). Nothing is uploaded.
IBANs and ID numbers from 14 countries are validated by their check digits, so order numbers and ISBNs are not mistaken for them.
It reads a sample per table, cannot read images or PDFs, and misses coded or abbreviated columns. It does not decide your lawful basis.
Made by Muhammad Shahmeer · Data Science MSc, University of Naples Federico II · © 2026, all rights reserved. Not legal advice. Not affiliated with the EDPB or any data protection authority.