Documentation Index
Fetch the complete documentation index at: https://docs.neuraltrust.ai/llms.txt
Use this file to discover all available pages before exploring further.
Data protection stops sensitive data from being sent to an LLM provider or emitted by the model. It is the most-used set of detections in TrustGate because it pairs with the action you really care about: Mask.
Like every other detection in TrustGate, you wire it up inline on a policy’s When condition — there’s no separate plugin screen.
Apply to prompts or responses
Data protection runs on either direction of the traffic. You control this with the condition’s Field:
| Field | What it protects | Typical use |
|---|
| Input | What the user sends to the model. | Prevent PII or secrets from being shipped to a third-party provider. |
| Output | What the model generates. | Prevent the LLM from echoing PII it learned, retrieved, or inferred. |
Where it lives in the picker
In Create Policy → When, the detection picker exposes two sibling categories for data protection:
| Category | Covers | Typical action |
|---|
| PII & Confidential | Personal and confidential entities — financial data, IDs, contact info, technical identifiers, international IDs. | Mask (most common), Block for the highest-severity entities. |
| Secrets & Keys | Credentials and machine identities — API keys, tokens, passwords, JWTs. | Block — secrets should never reach an LLM. |
Entity catalog
The catalog is grouped the same way it is in the engine. Every entity ships with a default mask placeholder that replaces the matched fragment on the wire.
Financial
| Entity | Detects | Default mask |
|---|
| Credit Card | Card numbers (all major brands). | [MASKED_CC] |
| CVV | Card verification values. | [MASKED_CVV] |
| Bank Account | Bank account numbers. | [MASKED_ACCOUNT] |
| IBAN | International Bank Account Numbers. | [MASKED_IBAN] |
| SWIFT / BIC | SWIFT/BIC codes. | [MASKED_BIC] |
| Routing Number | Bank routing numbers. | [MASKED_ROUTING] |
| Stripe Key | Stripe API keys. | [MASKED_API_KEY] |
Personal identification
| Entity | Detects | Default mask |
|---|
| SSN | US Social Security Numbers. | [MASKED_SSN] |
| Driver’s License | Driver’s license numbers. | [MASKED_LICENSE] |
| Passport | Passport numbers. | [MASKED_PASSPORT] |
| Tax ID | Tax identification numbers. | [MASKED_TAX_ID] |
| Entity | Detects | Default mask |
|---|
| Email | Email addresses. | [MASKED_EMAIL] |
| Phone Number | Phone numbers. | [MASKED_PHONE] |
| Address | Physical addresses. | [MASKED_ADDRESS] |
| ZIP Code | Postal codes. | [MASKED_ZIP] |
Technical identifiers
| Entity | Detects | Default mask |
|---|
| IP Address | IPv4 addresses. | [MASKED_IP] |
| IPv6 Address | IPv6 addresses. | [MASKED_IP6] |
| MAC Address | MAC addresses. | [MASKED_MAC] |
| UUID | Universally unique identifiers. | [MASKED_UUID] |
| Device IMEI | Device IMEI numbers. | [MASKED_IMEI] |
| Vehicle VIN | Vehicle identification numbers. | [MASKED_VIN] |
Authentication & security (Secrets & Keys)
These are the entities surfaced under the picker’s Secrets & Keys category — block them, don’t mask them.
| Entity | Detects | Default mask |
|---|
| Password | Password fields (password=secret123, dotenv lines, etc.). | [MASKED_PASSWORD] |
| API Key | Generic API keys (api_key=…). | [MASKED_API_KEY] |
| Access Token | Bearer / access tokens. | [MASKED_TOKEN] |
| JWT Token | JSON Web Tokens. | [MASKED_JWT_TOKEN] |
Cryptocurrency
| Entity | Detects | Default mask |
|---|
| Crypto Wallet | Cryptocurrency wallet addresses. | [MASKED_WALLET] |
International IDs — Europe
| Entity | Detects | Default mask |
|---|
| Spanish DNI | Spanish national ID. | [MASKED_DNI] |
| Spanish NIE | Spanish foreigner ID. | [MASKED_NIE] |
| Spanish CIF | Spanish company tax ID. | [MASKED_CIF] |
| Spanish NSS | Spanish social security. | [MASKED_NSS] |
| Spanish IBAN | Spanish IBAN. | [MASKED_ES_IBAN] |
| French NIR | French social security. | [MASKED_FR_NIR] |
| Italian CF | Italian fiscal code. | [MASKED_IT_CF] |
| German ID | German national ID. | [MASKED_DE_ID] |
International IDs — Latin America
| Entity | Detects | Default mask |
|---|
| Brazilian CPF | Brazilian individual taxpayer ID. | [MASKED_BR_CPF] |
| Brazilian CNPJ | Brazilian company registry. | [MASKED_BR_CNPJ] |
| Mexican CURP | Mexican personal ID. | [MASKED_MX_CURP] |
| Mexican RFC | Mexican tax ID. | [MASKED_MX_RFC] |
| Argentine DNI | Argentine national ID. | [MASKED_DNI] |
| Chilean RUT | Chilean tax ID. | [MASKED_RUT] |
| Colombian CC | Colombian citizen ID. | [MASKED_CC] |
| Peruvian DNI | Peruvian national ID. | [MASKED_DNI] |
Other
| Entity | Detects | Default mask |
|---|
| US Medicare | US Medicare beneficiary IDs. | [MASKED_MEDICARE] |
| ISIN | International Securities IDs. | [MASKED_ISIN] |
| Date | Dates (various formats). | [MASKED_DATE] |
Custom entities
When the built-in catalog isn’t enough, add custom detectors for entities that matter to you — internal customer IDs, ticket numbers, project codenames, regulated case identifiers. Custom entities are defined per workspace and show up in the same When picker alongside the built-in categories. They support:
- Keyword / dictionary lists for known vocabulary.
- Regex patterns for structured identifiers (
CASE-\d{6}, CUST-[A-Z0-9]{8}).
Once registered, they behave like any other detection — same Mask / Block / Log actions, same logs and metrics.
Masking — what Mask actually does
Picking Then → Mask on a data-protection policy does three things:
- Replaces the matched fragment in-flight with the entity’s default mask placeholder (
[MASKED_EMAIL], [MASKED_CC], [MASKED_SSN], …) before the request continues. The upstream provider and the model never see the original value.
- Logs the detection with the entity type and position — but not the original value. Logs carry the placeholder (and a hash if you enable it).
- Mirrors the redaction on the return path for the same entities, so a masked prompt and the model’s response stay consistent.
This is the difference between data protection and the other detection families: Mask actively rewrites the payload, while Block and Log only inspect it.
Using data protection in a policy
Standard Where / When / Then:
- Where — typically the
Gateway surface, optionally filtered by Routes or Upstreams. Use Browser if you want the same control on extension traffic.
- When —
Input · triggers · PII & Confidential: Email, Credit Card (and/or)Input · triggers · Secrets & Keys: API Key, JWT Token
- Then —
Mask for PII, Block for secrets.
A single policy can stack multiple detections — they AND together per the policy model. Use separate policies when you need different actions for different entities on the same route (e.g. Mask PII, Block secrets).
Common policies
- Mask PII before any third-party LLM call —
Where: Gateway · Routes /openai/*, /anthropic/* · When: Input · triggers · PII & Confidential · Then: Mask.
- Block secrets everywhere —
Where: Gateway · When: Input · triggers · Secrets & Keys · Then: Block. Duplicate on Output so the model can’t echo them back.
- Strip PII from generated responses —
Where: Gateway · When: Output · triggers · PII & Confidential: Email, Phone Number · Then: Mask.
- EU compliance — mask Spanish IDs on EU routes —
Where: Gateway · Upstreams = eu-* · When: Input + Output · triggers · PII & Confidential: Spanish DNI, Spanish NIE, Spanish NSS, Spanish IBAN · Then: Mask.
- LatAm compliance — mask national IDs on regional routes —
When: Input + Output · triggers · Brazilian CPF, Mexican CURP, Argentine DNI, Chilean RUT, Colombian CC, Peruvian DNI · Then: Mask.
- Log everything for a week, then enforce — clone any of the above with
Then: Log to baseline real traffic before flipping to Mask / Block.
