microsoft / microsoft/hve-core
feat(skills): add privacy-pii-detector skill for automated PII detection with industry overlays
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.5k
- Forks
- 301
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 92
Description
## Skill Name
privacy-pii-detector
## Programming Language
Markdown (knowledge-base skill with no executable scripts)
## Purpose
Automated PII/PI detection and privacy control verification for codebases. Scans for personal information processing patterns, classifies by sensitivity tier and industry, verifies protective controls exist, and raises findings when controls are missing. Requires zero privacy expertise from the user.
## Prerequisites
- Existing \privacy-standards\ skill (standards backbone)
- Existing \privacy-by-design\ skill (principle assessment — PR #2635)
- Privacy Reviewer agent (orchestrator)
## Value Proposition
| Without this skill | With this skill |
|---|---|
| User must know what PII exists in their code | Auto-detects PII from code patterns |
| No industry-specific PII awareness | Telco, Healthcare, Financial overlays with domain PII types |
| Privacy controls manually checked | Controls verified per PII tier automatically |
| No customization for org-specific data | \.pii-config.yml\ for custom types, tier overrides, suppressions |
| Findings are unstructured | YAML schema with backlog-ready handoff |
## Requirements
### Skill Behaviors
1. **Automated PII detection** — scan code for naming conventions, format patterns, schema definitions, API signatures, third-party SDKs, and log/telemetry leaks
2. **3-tier classification** — Identifiers (T1), Sensitive (T2), Special Category (T3) with 47+ core PII types
3. **Industry overlays** — Telco (IMEI, IMSI, CDR), Healthcare (MRN, FHIR), Financial (PAN, KYC) with extensible architecture
4. **Control verification** — for each detected PII, check encryption, access control, masking, retention, consent per tier
5. **Custom classification** — \.pii-config.yml\ for org-specific types, tier overrides, suppressions, catalog import (Purview, CSV)
6. **Structured findings** — YAML schema compatible with hve-core backlog handoff workflow
7. **Zero expertise required** — skill drives the entire assessment without user privacy knowledge
## Implementation
PR #2636 implements this skill with 9 files (~1,365 lines).
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing PR #2636, which contains the nine-file implementation referenced in this issue. Compare its skill behaviors, industry overlays, control verification, configuration, and YAML findings against the listed requirements; done means the complete privacy-pii-detector skill is implemented and the backlog handoff is covered.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- markdown
- Domain
- security
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100