PII redaction

To adhere to strict data residency laws (such as GDPR, HIPAA, and CCPA), sensitive Personally Identifiable Information (PII) must be shielded from third-party LLM environments. The Sentinel identifies and redacts PII before the prompt is forwarded to the upstream model.

Remediation action: Replace with {{REDACTED}} — The matched PII values are replaced with redaction placeholders before the prompt is forwarded to the LLM, allowing the request to proceed while protecting personal data.

What it detects

The guardrail covers a broad set of identifiers:

Group	Categories
Contact	Email addresses, US and international phone numbers
Government IDs	US Social Security numbers (SSN), passport numbers, driver's licenses, tax IDs / EINs, national IDs
Financial	Credit card numbers (Visa, Mastercard, Amex, Discover), IBANs, bank account numbers
Network & device	IPv4 and IPv6 addresses, MAC addresses
Vehicle	Vehicle Identification Numbers (VIN)
Medical	Dates of birth, medical record numbers (MRN)

Several of these (driver's license, tax ID, national ID, VIN, date of birth, medical record number) are detected from a keyword plus the identifier — for example, MRN: A1B2C3 — so the matcher keys off the surrounding label. Detection was tightened in this release to key off those labels more precisely (whole-word matching), reducing false positives while still catching the values that matter.

Example interception

Inbound prompt from application:

"Please draft a follow-up email to our customer John Smith ([email protected], phone 415-555-0132) regarding his recent invoice sent to credit card number 4532-1234-5678-9010."

What the upstream LLM actually sees:

"Please draft a follow-up email to our customer John Smith ({{REDACTED}}, phone {{REDACTED}}) regarding his recent invoice sent to credit card number {{REDACTED}}."

ℹ️
The customer name is left intact — the guardrail matches structured identifiers like those listed above, not free-text names.