Skill community intermediate
PII Classifier
Find PII in a dataset and propose the masking policy.
Scans column names and sample values for PII categories, then proposes classification tags and a masking/pseudonymisation policy.
npx de-agent-platform add pii-classifierAt a glance
| What | Find PII in a dataset and propose the masking policy. |
|---|---|
| Where | Security · tech-python · tech-snowflake |
Learning objectives
- Classify columns into PII categories
- Choose masking vs hashing vs tokenisation
- Record a data-classification tag
Security scan
Last sweep 2026-10-24: 0 finding(s), 0 marked as examples.
Details
PII Classifier
Caution
Sampling real data to find PII is itself a privacy action. Prefer metadata-only heuristics first; only sample with authorisation, and never persist samples.
Categories
Direct identifiers (name, email, phone, national ID), quasi-identifiers (postcode, DOB), sensitive attributes (health, financial), and free text (which can contain anything).
Policy mapping
Direct → mask or tokenise. Quasi → generalise. Free text → never expose raw in analytics; store separately with restricted access.
Registry stats
| Verification | community · Sep 10, 2026 |
|---|---|
| Completeness | 96 |
| Trust multiplier | ×0.5 |
| Composite | 34.4 · adequate |
| Freshness | 44 days since last source check |
| Difficulty | intermediate |
| Version | 0.1.1 |
| License | Apache-2.0 |
| Security flags | 3 |
Did this solve your problem?
PII Classifier