Data Classification Scanner

Updated May 13, 2026

What this skill does

Scans GitHub repositories, S3 buckets, and Google Drive for personally identifiable information (PII), protected health information (PHI), financial data, and other sensitive content. Classifies findings by data type and sensitivity level, maps data flows, and generates a comprehensive data classification report with remediation recommendations.

Example

PROMPT

We're a healthcare company subject to HIPAA and need to know where sensitive data lives before our annual compliance audit. Can you scan our 60 GitHub repos and 15 S3 buckets for PII and PHI? We also have a shared Google Drive with patient-facing documents. Need a classification report showing what we found, where it is, and what we should do about it.

OUTPUT

Data Classification Report — Healthcare Corp (HIPAA Scope) EXECUTIVE SUMMARY Total Findings: 47 across 3 data sources Critical (PHI): 12 — SSN, medical record IDs, patient names in code/config High (PII): 18 — Email, phone, addresses in repos and S3 Medium: 11 — Financial data, internal IDs Low (metadata): 6 — Sample data, test fixtures FINDINGS BY SOURCE | Source | Critical | High | Medium | Low | Total | |---------------|----------|------|--------|-----|-------| | GitHub (60) | 8 | 14 | 7 | 4 | 33 | | S3 (15) | 3 | 3 | 2 | 1 | 9 | | Google Drive | 1 | 1 | 2 | 1 | 5 | TOP FINDINGS (Critical) - patient-service/config: sample SSN in config template - analytics-export bucket: CSV with MRN + diagnosis codes - patient-portal repo: hardcoded test patient name in seed data REMEDIATION PRIORITIES 1. Remove PHI from patient-service config, use env vars 2. Encrypt S3 analytics-export bucket, enable access logging 3. Replace seed data with synthetic PHI in patient-portal Generated: Data flow map, sensitivity matrix, remediation checklist

Required Tools

GitHub

AWS

Google Drive

Compatible Agents

Claude

Cursor

Windsurf

ChatGPT

GitHub Copilot

Any MCP-compatible agent

Add to your agent

Download Skill

Or install via CLI:
$ npx skills add webrix-ai/agent-skills --skill data-classification-scanner

Deploy Org-wide

Provision to teams via RBAC

Identity-aware execution

Signed & verified skills

Full audit trail

Auto-bundled with required MCP servers

Use with

Free for up to 5 users

Related Skills

Abandoned Cart Recovery

Detects abandoned carts and triggers recovery workflows including email sequences, discount offers, and retargeting campaigns. Analyzes cart abandonment patterns to identify friction points in the checkout flow. Tracks recovery rate and revenue recaptured.

A/B Testing

Helps design statistically rigorous A/B tests for marketing campaigns, landing pages, and product features. Calculates required sample sizes, defines success metrics, sets up test variants, and analyzes results with confidence intervals. Prevents common testing mistakes like peeking and underpowered tests.

AI Adoption Dashboard Builder

Creates a multi-tab analytics dashboard for tracking AI tool adoption across your engineering organization. Includes executive KPIs, team-level adoption curves, per-tool usage breakdowns, productivity impact comparisons, and cost tracking. Optionally generates a Grafana dashboard JSON for real-time monitoring.

AI Adoption Readiness Assessment

A structured assessment framework that scores your organization across five critical dimensions of AI readiness. Produces an actionable scorecard with prioritized recommendations, a detailed gap analysis spreadsheet, and optional Jira tickets to track remediation efforts.

Your agents are already in the wild.

Give them a Basecamp. Go from AI chaos to AI work, in minutes.

Get Started

See a Demo