Does it overwrite my original files?

No, the skill is programmed to preserve original files, creating new anonymized versions and separate audit logs to ensure data integrity.

Is this skill GDPR compliant?

Yes, it provides irreversible strategies like masking and hashing which are specifically designed to meet full GDPR compliance requirements.

Which ML models does it use for detection?

It utilizes Scrubadub and spaCy (specifically the en_core_web_sm model) for high-accuracy Named Entity Recognition (NER) to find sensitive entities.

What types of data can this skill detect?

The skill identifies PII such as SSNs, email addresses, and phone numbers, as well as business-sensitive data including company names, revenue, costs, and pricing.

PII & Business Data Anonymizer

Name: PII & Business Data Anonymizer
Author: digital-stoic-org

bydigital-stoic-org

•

安全与测试

Protects sensitive information by detecting and anonymizing PII and confidential business data using ML-powered detection and customizable redaction strategies.

This skill enables developers and data scientists to safely handle sensitive files by scanning for Personally Identifiable Information (PII) like SSNs and emails, as well as business-sensitive data like revenue and pricing. By utilizing ML models like Scrubadub and spaCy, it offers five distinct anonymization strategies—masking, hashing, pseudonymization, tokenization, and mixed—allowing for flexible compliance with GDPR and HIPAA regulations during testing, demos, or data processing. It ensures data safety by generating audit logs and preventing the overwriting of original source files.

主要功能

01Automated audit logging and safety checks to prevent data leakage

02ML-powered detection of PII and sensitive business data using spaCy NER

03Comprehensive detection reports categorized by severity and entity type

04Five flexible anonymization strategies including masking, hashing, and tokenization

05GDPR and HIPAA aware workflows for regulatory compliance

064 GitHub stars

使用场景

01Anonymizing production datasets for use in product demos or case studies

02Automating compliance checks to ensure no PII is accidentally committed to repositories

03Redacting sensitive client data before sharing documents for collaborative code reviews

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add digital-stoic-org/agent-skills anonymize-doc

For use in Claude.ai and ChatGPT

Download Skill