environment-setup-guide
Guide developers through setting up development environments with proper tools, dependencies, and configurations
openevidence-security-basics
Apply OpenEvidence security best practices for HIPAA compliance and PHI protection. Use when securing API keys, implementing PHI handling, or auditing OpenEvidence security configuration. Trigger with phrases like "openevidence security", "openevidence hipaa", "openevidence phi", "secure openevid...
Full skill instructions
Security best practices for OpenEvidence integrations handling Protected Health Information (PHI) in compliance with HIPAA regulations.
# .env (NEVER commit to git)
OPENEVIDENCE_API_KEY=oe_live_***
OPENEVIDENCE_ORG_ID=org_***
OPENEVIDENCE_WEBHOOK_SECRET=whsec_***
# .gitignore (REQUIRED)
.env
.env.local
.env.*.local
*.pem
*.key
credentials*.json
// src/config/secrets.ts
// Use secret manager in production (AWS Secrets Manager, GCP Secret Manager, HashiCorp Vault)
import { SecretManagerServiceClient } from '@google-cloud/secret-manager';
const client = new SecretManagerServiceClient();
export async function getOpenEvidenceCredentials(): Promise<{
apiKey: string;
orgId: string;
}> {
const [apiKeyVersion] = await client.accessSecretVersion({
name: 'projects/my-project/secrets/openevidence-api-key/versions/latest',
});
const [orgIdVersion] = await client.accessSecretVersion({
name: 'projects/my-project/secrets/openevidence-org-id/versions/latest',
});
return {
apiKey: apiKeyVersion.payload!.data!.toString(),
orgId: orgIdVersion.payload!.data!.toString(),
};
}
// src/openevidence/phi-handler.ts
// IMPORTANT: OpenEvidence should NOT receive direct PHI in queries
interface SanitizedQuery {
question: string;
context: {
ageRange?: string; // "65-74" not exact age
sex?: string;
conditionCategories?: string[]; // "cardiovascular" not specific diagnosis
};
}
export function sanitizeQueryForOpenEvidence(
question: string,
patientContext?: PatientContext
): SanitizedQuery {
// Remove any PHI that might have leaked into the question
let sanitized = question;
// Remove potential names
sanitized = sanitized.replace(/\b(Mr\.|Mrs\.|Ms\.|Dr\.)\s+[A-Z][a-z]+\b/g, '[PATIENT]');
// Remove dates of birth
sanitized = sanitized.replace(/\b\d{1,2}[\/\-]\d{1,2}[\/\-]\d{2,4}\b/g, '[DATE]');
// Remove MRNs
sanitized = sanitized.replace(/\bMRN[:\s]*\d+\b/gi, '[MRN]');
// Remove SSNs
sanitized = sanitized.replace(/\b\d{3}-\d{2}-\d{4}\b/g, '[SSN]');
return {
question: sanitized,
context: patientContext ? {
ageRange: getAgeRange(patientContext.age),
sex: patientContext.sex,
conditionCategories: categorizeConditions(patientContext.conditions),
} : undefined,
};
}
function getAgeRange(age?: number): string | undefined {
if (!age) return undefined;
if (age < 18) return 'pediatric';
if (age < 40) return '18-39';
if (age < 65) return '40-64';
if (age < 75) return '65-74';
return '75+';
}
function categorizeConditions(conditions?: string[]): string[] | undefined {
// Map specific conditions to categories
const categoryMap: Record<string, string> = {
'hypertension': 'cardiovascular',
'diabetes': 'endocrine',
'asthma': 'pulmonary',
// ... more mappings
};
return conditions?.map(c => categoryMap[c.toLowerCase()] || 'other');
}
// src/openevidence/audit-log.ts
interface AuditEntry {
timestamp: Date;
eventType: 'query' | 'deepconsult' | 'access' | 'export';
userId: string;
userRole: string;
action: string;
resourceType: 'clinical_answer' | 'research_report';
resourceId?: string;
ipAddress: string;
userAgent: string;
success: boolean;
errorCode?: string;
// Never log the actual query content or response - may contain PHI
}
export class HIPAAAuditLogger {
private logStore: AuditLogStore;
constructor(store: AuditLogStore) {
this.logStore = store;
}
async logClinicalQuery(
userId: string,
userRole: string,
queryId: string,
success: boolean,
request: Request
): Promise<void> {
await this.logStore.insert({
timestamp: new Date(),
eventType: 'query',
userId,
userRole,
action: 'clinical_query',
resourceType: 'clinical_answer',
resourceId: queryId,
ipAddress: this.getClientIP(request),
userAgent: request.headers.get('user-agent') || 'unknown',
success,
});
}
async logDeepConsult(
userId: string,
userRole: string,
consultId: string,
success: boolean,
request: Request
): Promise<void> {
await this.logStore.insert({
timestamp: new Date(),
eventType: 'deepconsult',
userId,
userRole,
action: 'research_synthesis',
resourceType: 'research_report',
resourceId: consultId,
ipAddress: this.getClientIP(request),
userAgent: request.headers.get('user-agent') || 'unknown',
success,
});
}
private getClientIP(request: Request): string {
// Handle proxies
const forwarded = request.headers.get('x-forwarded-for');
if (forwarded) return forwarded.split(',')[0].trim();
return 'unknown';
}
}
// src/openevidence/webhook-security.ts
import crypto from 'crypto';
export function verifyWebhookSignature(
payload: string | Buffer,
signature: string,
secret: string,
tolerance: number = 300 // 5 minute tolerance
): boolean {
// Parse signature header: t=timestamp,v1=signature
const parts = signature.split(',').reduce((acc, part) => {
const [key, value] = part.split('=');
acc[key] = value;
return acc;
}, {} as Record<string, string>);
const timestamp = parseInt(parts['t']);
const providedSignature = parts['v1'];
// Check timestamp to prevent replay attacks
const now = Math.floor(Date.now() / 1000);
if (Math.abs(now - timestamp) > tolerance) {
console.error('Webhook timestamp too old or in future');
return false;
}
// Compute expected signature
const signedPayload = `${timestamp}.${payload}`;
const expectedSignature = crypto
.createHmac('sha256', secret)
.update(signedPayload)
.digest('hex');
// Timing-safe comparison
try {
return crypto.timingSafeEqual(
Buffer.from(providedSignature),
Buffer.from(expectedSignature)
);
} catch {
return false;
}
}
// src/openevidence/data-retention.ts
// HIPAA requires minimum 6-year retention of access logs
interface RetentionPolicy {
auditLogs: number; // days
queryResults: number; // days
deepConsultReports: number; // days
}
const HIPAA_RETENTION: RetentionPolicy = {
auditLogs: 2190, // 6 years
queryResults: 0, // Do not store (re-query as needed)
deepConsultReports: 365, // 1 year (user can re-run)
};
export class DataRetentionManager {
constructor(private policy: RetentionPolicy = HIPAA_RETENTION) {}
async cleanupExpiredData(): Promise<CleanupReport> {
const cutoffs = {
auditLogs: new Date(Date.now() - this.policy.auditLogs * 24 * 60 * 60 * 1000),
deepConsultReports: new Date(Date.now() - this.policy.deepConsultReports * 24 * 60 * 60 * 1000),
};
// Note: Audit logs should be archived, not deleted
const archivedLogs = await db.auditLogs.archive({
where: { timestamp: { lt: cutoffs.auditLogs } },
});
const deletedReports = await db.deepConsultReports.deleteMany({
where: { createdAt: { lt: cutoffs.deepConsultReports } },
});
return {
auditLogsArchived: archivedLogs.count,
reportsDeleted: deletedReports.count,
executedAt: new Date(),
};
}
}
| Security Issue | Detection | Mitigation |
|---|---|---|
| Exposed API key | Git scanning alert | Rotate immediately, audit access |
| PHI in query | Log pattern matching | Block request, alert compliance |
| Failed signature | Webhook verification | Reject webhook, alert security |
| Unauthorized access | Audit log review | Revoke access, investigate |
const auditLogger = new HIPAAAuditLogger(auditStore);
export async function secureClinicaQuery(
question: string,
patientContext: PatientContext | undefined,
user: AuthenticatedUser,
request: Request
): Promise<ClinicalResponse> {
// 1. Sanitize input
const sanitized = sanitizeQueryForOpenEvidence(question, patientContext);
// 2. Make query
const response = await client.query({
question: sanitized.question,
context: {
specialty: 'internal-medicine',
urgency: 'routine',
...sanitized.context,
},
});
// 3. Audit log
await auditLogger.logClinicalQuery(
user.id,
user.role,
response.id,
true,
request
);
return response;
}
For production deployment, see openevidence-prod-checklist.
Guide developers through setting up development environments with proper tools, dependencies, and configurations
Implement Exa lint rules, policy enforcement, and automated guardrails. Use when setting up code quality rules for Exa integrations, implementing pre-commit hooks, or configuring CI policy checks for Exa best practices. Trigger with phrases like "exa policy", "exa lint", "exa guardrails", "exa be...
Configure CI/CD pipelines for Documenso integrations. Use when setting up automated testing, deployment pipelines, or continuous integration for Documenso projects. Trigger with phrases like "documenso CI", "documenso GitHub Actions", "documenso pipeline", "documenso automated testing".
Build check model availability and implement fallback chains. Use when building resilient systems or handling model outages. Trigger with phrases like 'openrouter availability', 'openrouter fallback', 'openrouter model down', 'openrouter health check'.
Configure Langfuse enterprise organization management and access control. Use when implementing team access controls, configuring organization settings, or setting up role-based permissions for Langfuse projects. Trigger with phrases like "langfuse RBAC", "langfuse teams", "langfuse organization"...
Execute compliance and security auditing for Cursor usage. Triggers on "cursor compliance", "cursor audit", "cursor security review", "cursor soc2", "cursor gdpr". Use when analyzing or auditing cursor compliance audit. Trigger with phrases like "cursor compliance audit", "cursor audit", "cursor".
Configure Apollo.io CI/CD integration. Use when setting up automated testing, continuous integration, or deployment pipelines for Apollo integrations. Trigger with phrases like "apollo ci", "apollo github actions", "apollo pipeline", "apollo ci/cd", "apollo automated tests".
Create robust Python automation with full logging and safety checks. Use when tasks need complex data processing, authenticated API work, conditional file operations, or error handling beyond simple shell commands.
Configure PostHog across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment secrets, or implementing environment-specific PostHog configurations. Trigger with phrases like "posthog environments", "posthog staging", "po...
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.
Validate insecure deserialization checker operations. Auto-activating skill for Security Fundamentals. Triggers on: insecure deserialization checker, insecure deserialization checker Part of the Security Fundamentals skill category. Use when working with insecure deserialization checker functiona...
Manage path traversal finder operations. Auto-activating skill for Security Fundamentals. Triggers on: path traversal finder, path traversal finder Part of the Security Fundamentals skill category. Use when working with path traversal finder functionality. Trigger with phrases like "path traversa...
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience