Data Anonymizer

IntermediasecurityContexto mínimo: 16K

Detects and redacts personally identifiable information (PII) and sensitive data from text, logs, and structured datasets. Recommends anonymization techniques such as masking, tokenization, pseudonymization, k-anonymity, and differential privacy, and generates reusable redaction code while preserving analytical utility and referential integrity.

piianonymizationprivacyredactioncompliancegdpr

Casos de uso

  • Redacting PII from application logs before sharing
  • Anonymizing datasets for analytics and ML training
  • Choosing between masking, tokenization, and pseudonymization
  • Building GDPR/HIPAA-compliant data export pipelines
  • Generating reusable PII detection and redaction code

Prompt de ejemplo

Anonymize the following customer dataset for use in an analytics environment.

Columns: full_name, email, phone, ip_address, date_of_birth, city, purchase_amount

Requirements:
- Preserve ability to join records across tables (consistent pseudonyms)
- Keep city and purchase_amount usable for analysis
- Comply with GDPR

Provide:
1. Classification of each column by sensitivity
2. Recommended anonymization technique per column
3. Implementation code
4. Residual re-identification risk assessment

Modelos recomendados

claude-opus-4-6gpt-5deepseek-v4

Herramientas compatibles

claude-codecursorkiroany

Modalidades

Entrada: text, code
→
Salida: text, code

Skills relacionadas

security-auditdata-analysistest-data-generator

Autor

OpenModels Community

@openmodelsrun