pii-guard

Filter personally identifiable information and sensitive financial data from AI-generated text.

18|5|Updated Jan 21, 2026
One-click install
npx skills add https://github.com/ddalcu/agent-orcha --skill pii-guard
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pii-guard
Source: https://github.com/ddalcu/agent-orcha/tree/main/templates/skills/pii-guard
Command: npx skills add https://github.com/ddalcu/agent-orcha --skill pii-guard

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill protects sensitive personal and financial information from being exposed in AI-generated responses, ensuring compliance with data privacy policies.

Core Features & Use Cases

  • PII Detection and Masking: Identifies and omits sensitive data like SSNs, financial details, and personal contact information.
  • Policy Enforcement: Adheres to company data policies by refusing to process or store explicit PII.
  • Use Case: When an agent is asked to summarize customer feedback that might contain email addresses or phone numbers, this Skill ensures those details are masked or removed before the summary is presented.

Quick Start

Ensure that no personally identifiable information is included in the output.

Frequently Asked Questions about pii-guard

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

FAQPage Schema
How do I filter personally identifiable information from AI-generated text?

You can filter personally identifiable information by applying data handling protocols that omit or mask sensitive details like government identifiers, compensation details, and personal contact information from generated text.

What is the best way to mask sensitive financial data in customer feedback summaries?

The best way to mask sensitive financial data in summaries is to use a Skill that detects compensation details and personal contact information, automatically removing or masking them before presenting the final output.

Can I use this to enforce data privacy policies for user-provided information?

Yes, you can enforce data privacy policies for user-provided information because the Skill adheres to a strict data handling protocol, refusing to process or store explicit PII like SSNs and financial details.

Does data masking work on government identifiers like SSNs in generated responses?

Data masking works on government identifiers like SSNs by detecting specific categories of sensitive data within the text and automatically omitting or masking them to ensure compliance with data privacy requirements.

What are the limitations of filtering PII from AI text completions?

A limitation of filtering PII is that the Skill requires adherence to a strict data handling protocol for user-provided information, relying on policy enforcement to omit or mask specific sensitive categories rather than encrypting them.