GDPRcriticalv1.0.0 · System

Special Category Data Block

Blocks processing of GDPR Art. 9 special category data (health, racial origin, religion, biometric) unless explicit lawful basis is established.

📘Clone & start observing

Creates a Guideline policy. Observation only — nothing is blocked until you promote to Strict.

Mode on clone: log

Policy name

Defaults to template name. Customise to distinguish multiple instances of the same template.

Leave empty to apply broadly via the template's default data-classification / risk-tier filters.

Rationale

Art. 9 prohibits processing of special categories without explicit consent or other lawful basis. This policy provides a hard block at the input boundary.

Example violation

Prompt mentions: "patient diagnosed with HIV positive seeking life insurance quote"

Triggers (1)

inputScan prompts for special category data

Detectors (3)

keyword_listhealth-terms
Health/medical terminology
keyword_listreligion-terms
Religion/belief terminology
keyword_listbiometric-terms
Biometric data terminology

Actions (3)

blockReject with explanation
require_reviewAllow override only by DPO
logRecord blocked attempt

Tunable parameters (4)

Health terms

advancedkeywords

Terms triggering Art. 9 health processing concern.

Default: ["HIV","diabetes","cancer","diagnosed","prescription","patient","medical condition"]

Religion/belief terms

advancedkeywords

Terms triggering Art. 9 religious-data concern.

Default: ["Christian","Muslim","Jewish","Hindu","atheist","religious belief"]

Biometric terms

advancedkeywords

Terms triggering Art. 9 biometric concern.

Default: ["fingerprint","facial recognition","iris scan","DNA","biometric"]

Role allowed to override

basicstring

Only this role can override the block.

Default: "DPO"

Regulatory references

GDPR Art. 9

Template defaults (suggested target after promotion)

Suggested mode

block

Risk tiers

—

Data classifications

—

Departments

—

Cloned policies start in Guideline mode. Use the promotion wizard to flip to Strict once you trust the false-positive rate.