exa-data-handling
Implement Exa PII handling, data retention, and GDPR/CCPA compliance patterns.Use when handling sensitive data, implementing data redaction, configuring retention policies,or ensuring compliance with privacy regulations for Exa integrations.Trigger with phrases like "exa data", "exa PII","exa GDPR", "exa data retention", "exa privacy", "exa CCPA".
When & Why to Use This Skill
The Exa Data Handling skill provides a comprehensive framework for managing PII, enforcing data retention, and ensuring GDPR/CCPA compliance within Exa integrations. It empowers developers to build privacy-conscious AI agents by automating sensitive data detection, redaction, and regulatory workflows, ensuring that enterprise-grade security standards are met during data processing.
Use Cases
- PII Detection & Redaction: Automatically identify and mask sensitive information such as emails, phone numbers, and credit card details in logs to prevent accidental data exposure.
- Regulatory Compliance: Streamline GDPR and CCPA workflows, including handling Data Subject Access Requests (DSAR) and executing the 'Right to Erasure' across Exa-related datasets.
- Automated Data Retention: Implement scheduled cleanup tasks to purge non-essential logs and business metrics after defined periods, reducing legal liability and storage overhead.
- Data Minimization: Configure API integration patterns to request and store only the minimum necessary data fields, adhering to privacy-by-design principles.
| name | exa-data-handling |
|---|---|
| description | | |
| allowed-tools | Read, Write, Edit |
| version | 1.0.0 |
| license | MIT |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
Exa Data Handling
Overview
Handle sensitive data correctly when integrating with Exa.
Prerequisites
- Understanding of GDPR/CCPA requirements
- Exa SDK with data export capabilities
- Database for audit logging
- Scheduled job infrastructure for cleanup
Data Classification
| Category | Examples | Handling |
|---|---|---|
| PII | Email, name, phone | Encrypt, minimize |
| Sensitive | API keys, tokens | Never log, rotate |
| Business | Usage metrics | Aggregate when possible |
| Public | Product names | Standard handling |
PII Detection
const PII_PATTERNS = [
{ type: 'email', regex: /[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}/g },
{ type: 'phone', regex: /\b\d{3}[-.]?\d{3}[-.]?\d{4}\b/g },
{ type: 'ssn', regex: /\b\d{3}-\d{2}-\d{4}\b/g },
{ type: 'credit_card', regex: /\b\d{4}[- ]?\d{4}[- ]?\d{4}[- ]?\d{4}\b/g },
];
function detectPII(text: string): { type: string; match: string }[] {
const findings: { type: string; match: string }[] = [];
for (const pattern of PII_PATTERNS) {
const matches = text.matchAll(pattern.regex);
for (const match of matches) {
findings.push({ type: pattern.type, match: match[0] });
}
}
return findings;
}
Data Redaction
function redactPII(data: Record<string, any>): Record<string, any> {
const sensitiveFields = ['email', 'phone', 'ssn', 'password', 'apiKey'];
const redacted = { ...data };
for (const field of sensitiveFields) {
if (redacted[field]) {
redacted[field] = '[REDACTED]';
}
}
return redacted;
}
// Use in logging
console.log('Exa request:', redactPII(requestData));
Data Retention Policy
Retention Periods
| Data Type | Retention | Reason |
|---|---|---|
| API logs | 30 days | Debugging |
| Error logs | 90 days | Root cause analysis |
| Audit logs | 7 years | Compliance |
| PII | Until deletion request | GDPR/CCPA |
Automatic Cleanup
async function cleanupExaData(retentionDays: number): Promise<void> {
const cutoff = new Date();
cutoff.setDate(cutoff.getDate() - retentionDays);
await db.exaLogs.deleteMany({
createdAt: { $lt: cutoff },
type: { $nin: ['audit', 'compliance'] },
});
}
// Schedule daily cleanup
cron.schedule('0 3 * * *', () => cleanupExaData(30));
GDPR/CCPA Compliance
Data Subject Access Request (DSAR)
async function exportUserData(userId: string): Promise<DataExport> {
const exaData = await exaClient.getUserData(userId);
return {
source: 'Exa',
exportedAt: new Date().toISOString(),
data: {
profile: exaData.profile,
activities: exaData.activities,
// Include all user-related data
},
};
}
Right to Deletion
async function deleteUserData(userId: string): Promise<DeletionResult> {
// 1. Delete from Exa
await exaClient.deleteUser(userId);
// 2. Delete local copies
await db.exaUserCache.deleteMany({ userId });
// 3. Audit log (required to keep)
await auditLog.record({
action: 'GDPR_DELETION',
userId,
service: 'exa',
timestamp: new Date(),
});
return { success: true, deletedAt: new Date() };
}
Data Minimization
// Only request needed fields
const user = await exaClient.getUser(userId, {
fields: ['id', 'name'], // Not email, phone, address
});
// Don't store unnecessary data
const cacheData = {
id: user.id,
name: user.name,
// Omit sensitive fields
};
Instructions
Step 1: Classify Data
Categorize all Exa data by sensitivity level.
Step 2: Implement PII Detection
Add regex patterns to detect sensitive data in logs.
Step 3: Configure Redaction
Apply redaction to sensitive fields before logging.
Step 4: Set Up Retention
Configure automatic cleanup with appropriate retention periods.
Output
- Data classification documented
- PII detection implemented
- Redaction in logging active
- Retention policy enforced
Error Handling
| Issue | Cause | Solution |
|---|---|---|
| PII in logs | Missing redaction | Wrap logging with redact |
| Deletion failed | Data locked | Check dependencies |
| Export incomplete | Timeout | Increase batch size |
| Audit gap | Missing entries | Review log pipeline |
Examples
Quick PII Scan
const findings = detectPII(JSON.stringify(userData));
if (findings.length > 0) {
console.warn(`PII detected: ${findings.map(f => f.type).join(', ')}`);
}
Redact Before Logging
const safeData = redactPII(apiResponse);
logger.info('Exa response:', safeData);
GDPR Data Export
const userExport = await exportUserData('user-123');
await sendToUser(userExport);
Resources
Next Steps
For enterprise access control, see exa-enterprise-rbac.