PII Masker

Overview

Masks common PII patterns (email, phone, credit card, IP, IBAN) using deterministic regex detectors. Supports token and asterisk masking styles. Credit card validation uses Luhn check. Accepts file input via file_ref — no need to extract file content first.

Before you log or share text, we mask common PII patterns deterministically so redaction is reproducible and auditable — not left to model guesswork.

When to use it

Scope

Non-goals

• Not exhaustive PII detection — regex-based, may miss context-dependent PII
• Does not use ML/NLP-based detection or named entity recognition
• Not suitable as sole compliance mechanism — supplement with manual review
• Locale-bound: phone patterns are tuned for common North American formats and IBAN for European accounts; other national ID or phone schemes are not detected

Properties

Capabilities

Cost & billing

Flat rate per invocation

File handling

File limits

Constraints this skill applies to your input and generated files. The “Limited by” column shows the static source of each cap; none of these can be raised by upgrading your plan.

How we handle your data

Input schema

Output schema

API contract

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"text.mask_pii","input":{"text":"Email [email protected] or call 555-123-4567"}}'

import { Squillify } from "@squillify/sdk";

const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });

const { output } = await sq.execute("text.mask_pii", {"text":"Contact me at [email protected] or call 555-123-4567 regarding order #12345"});

Errors

Other limits

Limitations

• Not exhaustive PII detection — regex-based, may miss context-dependent PII
• Does not use ML/NLP-based detection or named entity recognition
• Not suitable as sole compliance mechanism — supplement with manual review
• Locale-bound: phone patterns are tuned for common North American formats and IBAN for European accounts; other national ID or phone schemes are not detected
• Compliance-grade PII removal requiring legal certification
• Named entity recognition of people, organizations, or locations
• Detecting context-dependent PII like names or addresses without patterns

How to call

POST /v1/execute (requires authentication)

{
  "skillKey": "text.mask_pii",
  "input": {
    "text": "Contact me at [email protected] or call 555-123-4567 regarding order #12345"
  }
}

Examples

{
  "text": "Contact me at [email protected] or call 555-123-4567 regarding order #12345"
}

{
  "warnings": [
    "PII detection is regex-based and not exhaustive"
  ],
  "detectionCount": 2,
  "countsByType": {
    "PHONE": 1,
    "EMAIL": 1
  },
  "maskStyle": "token",
  "maskedText": "Contact me at [EMAIL] or call [PHONE] regarding order #12345"
}

{
  "text": "Server 10.0.14.22 logged [email protected]",
  "preserveLength": true,
  "maskStyle": "asterisk"
}

{
  "warnings": [
    "PII detection is regex-based and not exhaustive"
  ],
  "detectionCount": 2,
  "countsByType": {
    "IP_ADDRESS": 1,
    "EMAIL": 1
  },
  "maskStyle": "asterisk",
  "maskedText": "Server ********** logged *****************"
}

{
  "file_ref": "squillify://files/f-abc123def456",
  "outputToFile": true
}

{
  "maskStyle": "token",
  "file_ref": "squillify://files/f-masked-xyz789",
  "download_url": "https://api.squillify.com/v1/files/f-masked-xyz789/download",
  "detectionCount": 47,
  "countsByType": {
    "EMAIL": 23,
    "PHONE": 15,
    "IP_ADDRESS": 9
  },
  "size_bytes": 154200,
  "warnings": [
    "PII detection is regex-based and not exhaustive"
  ]
}

Recommended use cases

• Redact PII from text before logging or storing in analytics systems
• Anonymize customer messages before sharing with third parties
• Sanitize training data by masking identifiable patterns

Avoid for

• Compliance-grade PII removal requiring legal certification
• Named entity recognition of people, organizations, or locations
• Detecting context-dependent PII like names or addresses without patterns

Related skills

Composable with

Safety & privacy

• Runs without calling any external service.
• Your payloads are never stored permanently.
• Telemetry captures metadata only — never your payload contents.
• We never train models on your payloads.
• No human reviews your payloads.

Tags