Detect PII Columns

data.detect_pii_columns

ProductionHeuristic (Class C)Deterministicbest-effortfastv1.0.0

No network

Overview

When you send column names and sample values, we classify likely PII using deterministic validators (email, phone, IBAN, IP, UUID, credit card) plus column-name hints — hints alone never reach high confidence. This is best-effort review support; absence of a finding is not proof of absence. We do not return raw matched values by default.

PII review needs deterministic signals, not LLM guesses about column content.

Reliability

Best-effort by design. The same samples give the same verdicts while detectorProfile stays put, and an upgrade to that profile can reclassify a column, so keep the value alongside your findings. Strong signals come from validating the values themselves — a checksum-valid IBAN, a Luhn-valid card number, a well-formed email, phone, UUID or IP; a promising heading on its own never scores above 0.4, and we never guess protected attributes such as health, religion or ethnicity. A quiet result is not a clean bill of health: we say so in every response through the PII_DETECTION_LIMITATION warning. Two errors can come back: PII_COLUMN_LIMIT_EXCEEDED — trigger: you sent more than 1,000 columns; retryable: no; next: split the schema and scan it in batches. PII_SAMPLE_LIMIT_EXCEEDED — trigger: a column carries more values than we are willing to read; retryable: no; next: send at most 1,000 sample values per column. In practice we simply stop reading a column once we hit the sample limit, so you should rarely meet the second one.

Context footprint

Returns per-column classifications, datasetRisk, warnings, detectorProfile, _meta. A successful call costs 1 execution credit.

When to use it

Before anonymization or export, to see which columns likely hold personal data.

As proof that a dataset contains no PII or for compliance sign-off.

Scope

Note

Flags columns likely to contain PII from samples you provide.

Non-goals

Does not certify PII-free data
Does not infer protected attributes
Does not return raw values by default

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

analysisvalidation

Cost & billing

Flat rate per invocation

MetercallsBillable onsuccessCost per call1 credit

File handling

Accepts file_refProduces file_refMax input2 MB

How we handle your data

Sensitive processing

What this means

This skill is designed to detect, mask, redact, validate, or otherwise process sensitive data.

Squillify guarantees

Runs inside Squillify
This skill runs inside Squillify.
Payloads are not sent to an external service by this skill.
Squillify does not permanently store submitted payloads.
Telemetry records metadata only, not submitted content.
Submitted payloads are not used for training.
Submitted payloads are not reviewed by humans.
Targets sensitive data
Output contains sensitive findings

Your responsibility

Squillify does not determine whether submitted content is sensitive. Your application is responsible for deciding what data it is allowed to submit. Your application is responsible for securing the response.

Read the Microskill Data Handling Policy

Input schema

Field	Type	Required	Description
columns	array	Yes	Bounded array of 1 through 1000 closed sampled columns in heading order.
profile	string	No	Regional preset echoed in _meta; omit it for global_general.
options	object	No	Closed optional detection knobs; omit the object to keep the published defaults.

Output schema

Field	Type	Required	Description
columns	array	Yes	Bounded array of 1 through 1000 closed per-column verdicts in input order.
datasetRisk	object	Yes	Closed dataset-level PII risk summary with totalColumns, likelyPiiColumns and riskLevel.
warnings	array	Yes	Bounded array of 1 through 8 closed findings; currently always the PII_DETECTION_LIMITATION warning.
detectorProfile	string	Yes	Pinned detector set that produced these verdicts.
_meta	object	No	Closed provenance for the detector preset and supported types.

API contract

POST /v1/execute

curl

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"data.detect_pii_columns","input":{"columns":[{"name":"email","values":["[email protected]"]}]}}'

Integrations

TypeScript SDK

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

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

const { output } = await sq.execute("data.detect_pii_columns", {"columns":[{"values":["[email protected]","[email protected]"],"name":"email"}]});

Errors

Code	HTTP	Retryable	Description
VALIDATION_ERROR	400	No	The request payload failed schema validation.
UNAUTHORIZED	401	No	Missing or invalid API key.
SKILL_NOT_ACCESSIBLE	403	No	The API key is not granted access to this skill.
SKILL_NOT_AVAILABLE_FOR_PLAN	403	No	This skill is not included in your current plan.
PLAN_ELIGIBILITY_UNAVAILABLE	503	Yes	Plan eligibility could not be decided. Retry after backoff.
SKILL_NOT_FOUND	404	No	The requested skill or version does not exist.
TENANT_RATE_LIMITED	429	Yes	Request rate limit exceeded. Retry after backoff.
QUOTA_EXCEEDED	429	Yes	Plan quota exhausted. Retryable once the quota period resets.
EXECUTION_TIMEOUT	504	Yes	Execution exceeded the allowed time budget.
PII_COLUMN_LIMIT_EXCEEDED	429	No	A size, quota, rate, or time limit was exceeded.
PII_SAMPLE_LIMIT_EXCEEDED	429	No	A size, quota, rate, or time limit was exceeded.

Other limits

Limit	Value
Recommended inline bytes	32 KiB

Limitations

Does not certify PII-free data
Does not infer protected attributes
Does not return raw values by default
Regulatory certification of anonymity
Proof that no PII exists

How to call

POST /v1/execute (requires authentication)

Request bodyjson

{
  "skillKey": "data.detect_pii_columns",
  "input": {
    "columns": [
      {
        "values": [
          "[email protected]",
          "[email protected]"
        ],
        "name": "email"
      }
    ]
  }
}

Examples

Email column detected by validator

Inputjson

{
  "columns": [
    {
      "values": [
        "[email protected]",
        "[email protected]"
      ],
      "name": "email"
    }
  ]
}

Expected outputjson

{
  "warnings": [
    {
      "code": "PII_DETECTION_LIMITATION",
      "message": "notDetectedDoesNotMeanAbsent: absence of a finding is not proof that no PII is present",
      "severity": "warning"
    }
  ],
  "_meta": {
    "supportedTypes": [
      "email",
      "iban",
      "uuid",
      "ip_address",
      "phone",
      "credit_card"
    ],
    "profile": "global_general"
  },
  "datasetRisk": {
    "likelyPiiColumns": 1,
    "totalColumns": 1,
    "riskLevel": "medium"
  },
  "detectorProfile": "pii-detectors-1",
  "columns": [
    {
      "columnNameHint": true,
      "confidence": 0.99,
      "matchCount": 2,
      "likelyPii": true,
      "reason": "value_validator",
      "nonNullSamples": 2,
      "column": "email",
      "classification": "email"
    }
  ]
}

Phone column with E.164 samples