pii-detect

Detect and flag personally identifiable information in text, code, and configurations.

70.1k|8.4k|Updated Jun 2, 2025
One-click install
npx skills add https://github.com/ruvnet/claude-flow --skill pii-detect
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pii-detect
Source: https://github.com/ruvnet/claude-flow/tree/main/plugins/ruflo-aidefence/skills/pii-detect
Command: npx skills add https://github.com/ruvnet/claude-flow --skill pii-detect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Sensitive data like emails, phone numbers, SSNs, API keys, and passwords can accidentally leak into commits, logs, stored data, or model responses. This Skill scans content before it is persisted or shared so PII can be flagged and redacted before exposure.

Core Features & Use Cases

  • Quick Boolean Check: Run a fast has-PII check on any text to get a simple yes/no answer before committing or logging.
  • Categorized Detection: Identify specific PII types including emails, phone numbers, SSNs, tax IDs, credit cards, API keys, tokens, passwords, and physical addresses.
  • Context-Aware Analysis: Perform deeper analysis to find names linked to sensitive data and suggest redaction for flagged locations.
  • Use Case: Before pushing a commit, scan the diff for hardcoded credentials or customer emails, then redact the flagged values before the code reaches the repository.

Quick Start

Scan this text for any personally identifiable information and flag anything that should be redacted before I commit it.

Frequently Asked Questions about pii-detect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect PII in text before committing code?

Run a quick boolean PII check on the text first, then use the detailed scan to get categorized findings such as emails, API keys, or SSNs. Flag the specific locations and redact them before committing.

What types of PII can be detected in code and logs?

Detection covers email addresses, phone numbers, social security numbers, tax IDs, credit card numbers, API keys, tokens, passwords, physical addresses, and names linked to sensitive data.

Can PII detection scan model responses before sending them?

Yes, the skill is designed to screen model responses, logs, stored data, and commits. Use the context-aware analysis for responses where names may be linked to sensitive data.

What is the difference between a quick PII check and full analysis?

The quick check returns a boolean indicating whether any PII exists, while full analysis provides context-aware detection with categorized findings and redaction suggestions for each flagged location.

When should I not rely on automated PII detection?

Automated detection may miss obfuscated, encoded, or non-standard PII formats such as concatenated identifiers or domain-specific ID schemes. Combine scanning with manual review for high-sensitivity data pipelines.