本文へ移動
cccskills
無料GitHub で公開

abridge-security-basics

Apply HIPAA-compliant security practices for Abridge clinical AI integrations. Use when securing PHI in transit/at rest, configuring access controls, implementing audit logging, or preparing for HIPAA security audits. Trigger: "abridge security", "abridge HIPAA", "abridge PHI protection", "abridge access control", "abridge audit logging".

インストール方法を見る

含まれるファイル(2)

  • SKILL.md6.9 KB
  • source.json897 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Abridge Security Basics

Overview

HIPAA-compliant security configuration for Abridge clinical AI integrations. Abridge handles PHI (Protected Health Information) — security is not optional. This skill covers encryption, access control, audit logging, and BAA requirements.

HIPAA Security Checklist

RequirementImplementationStatus
Encryption in transitTLS 1.3 enforcedRequired
Encryption at restAES-256 for stored PHIRequired
Access controlRole-based with MFARequired
Audit loggingAll PHI access loggedRequired
BAA signedBusiness Associate AgreementRequired
Minimum necessaryOnly access needed PHIRequired
Breach notification60-day notification planRequired

Instructions

Step 1: Enforce TLS and Certificate Pinning

// src/security/tls-config.ts
import https from 'https';
import axios from 'axios';

const abridgeHttpsAgent = new https.Agent({
  minVersion: 'TLSv1.3',           // Enforce TLS 1.3 minimum
  rejectUnauthorized: true,         // Never disable cert validation
  // Optional: certificate pinning for Abridge API
  // ca: fs.readFileSync('./certs/abridge-ca.pem'),
});

const secureClient = axios.create({
  baseURL: process.env.ABRIDGE_BASE_URL,
  httpsAgent: abridgeHttpsAgent,
  headers: {
    'Authorization': `Bearer ${process.env.ABRIDGE_CLIENT_SECRET}`,
    'X-Org-Id': process.env.ABRIDGE_ORG_ID!,
    'Strict-Transport-Security': 'max-age=31536000; includeSubDomains',
  },
});

Step 2: PHI-Safe Audit Logger

// src/security/audit-logger.ts
interface AuditEntry {
  timestamp: string;
  action: 'create' | 'read' | 'update' | 'delete' | 'access';
  resource_type: 'session' | 'note' | 'transcript' | 'patient_summary';
  resource_id: string;           // Session/note ID (not PHI)
  actor: string;                 // Provider NPI or system ID
  ip_address: string;
  success: boolean;
  // NEVER include: patient name, DOB, SSN, MRN, diagnosis, note content
}

class HipaaAuditLogger {
  private entries: AuditEntry[] = [];

  log(entry: Omit<AuditEntry, 'timestamp'>): void {
    const fullEntry: AuditEntry = {
      ...entry,
      timestamp: new Date().toISOString(),
    };

    // Validate no PHI leaked into audit log
    const serialized = JSON.stringify(fullEntry);
    if (this.containsPhi(serialized)) {
      console.error('CRITICAL: PHI detected in audit entry — entry blocked');
      return;
    }

    this.entries.push(fullEntry);
    // In production: write to HIPAA-compliant log store (CloudWatch, Splunk, etc.)
    console.log(`AUDIT: ${JSON.stringify(fullEntry)}`);
  }

  private containsPhi(text: string): boolean {
    const phiPatterns = [
      /\b\d{3}-\d{2}-\d{4}\b/,        // SSN
      /\b[A-Z]\d{8}\b/,               // MRN pattern
      /\b\d{1,2}\/\d{1,2}\/\d{4}\b/,  // DOB
    ];
    return phiPatterns.some(p => p.test(text));
  }

  getRetentionPolicy(): { minYears: number; note: string } {
    return {
      minYears: 6,
      note: 'HIPAA requires audit logs retained for minimum 6 years',
    };
  }
}

export { HipaaAuditLogger, AuditEntry };

Step 3: Role-Based Access Control

// src/security/rbac.ts
type AbridgeRole = 'clinician' | 'nurse' | 'admin' | 'billing' | 'integration_service';

interface AbridgePermissions {
  canCreateSession: boolean;
  canViewNotes: boolean;
  canViewPatientSummary: boolean;
  canExportData: boolean;
  canManageProviders: boolean;
  canAccessBilling: boolean;
}

const ROLE_PERMISSIONS: Record<AbridgeRole, AbridgePermissions> = {
  clinician: {
    canCreateSession: true, canViewNotes: true, canViewPatientSummary: true,
    canExportData: false, canManageProviders: false, canAccessBilling: false,
  },
  nurse: {
    canCreateSession: true, canViewNotes: true, canViewPatientSummary: true,
    canExportData: false, canManageProviders: false, canAccessBilling: false,
  },
  admin: {
    canCreateSession: false, canViewNotes: false, canViewPatientSummary: false,
    canExportData: true, canManageProviders: true, canAccessBilling: true,
  },
  billing: {
    canCreateSession: false, canViewNotes: false, canViewPatientSummary: false,
    canExportData: false, canManageProviders: false, canAccessBilling: true,
  },
  integration_service: {
    canCreateSession: true, canViewNotes: true, canViewPatientSummary: false,
    canExportData: false, canManageProviders: false, canAccessBilling: false,
  },
};

function checkPermission(role: AbridgeRole, action: keyof AbridgePermissions): boolean {
  return ROLE_PERMISSIONS[role]?.[action] ?? false;
}

Step 4: Secrets Management

// src/security/secrets.ts
// Never hardcode credentials — use environment or secret manager

async function loadAbridgeSecrets(): Promise<Record<string, string>> {
  // Option 1: Environment variables (minimum viable)
  // Option 2: AWS Secrets Manager / GCP Secret Manager (recommended)
  // Option 3: HashiCorp Vault (enterprise)

  // Example: GCP Secret Manager
  const { SecretManagerServiceClient } = await import('@google-cloud/secret-manager');
  const client = new SecretManagerServiceClient();

  const secrets: Record<string, string> = {};
  const secretNames = ['abridge-client-secret', 'abridge-org-id', 'epic-client-secret'];

  for (const name of secretNames) {
    const [version] = await client.accessSecretVersion({
      name: `projects/${process.env.GCP_PROJECT}/secrets/${name}/versions/latest`,
    });
    secrets[name] = version.payload?.data?.toString() || '';
  }

  return secrets;
}

Output

  • TLS 1.3 enforcement with optional cert pinning
  • HIPAA-compliant audit logger with PHI leak detection
  • Role-based access control matrix
  • Secrets loaded from cloud secret manager

Error Handling

IssueCauseSolution
TLS handshake failureServer doesn't support TLS 1.3Verify Abridge endpoint; check proxy
PHI in logsAudit logger bypassAdd PHI detection to all log paths
Permission deniedWrong roleCheck RBAC matrix for required role

Resources

Next Steps

For production deployment checklist, see abridge-prod-checklist.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

007

無料

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

日本語の概要は準備中です。原文の説明を表示しています。

aibot88/sec_skill_store42026年5月27日 更新

Guides the creation of agile user stories and Gherkin feature files. Use when the user wants to create a user story, write acceptance criteria, define Gherkin scenarios, or author BDD feature files. This should trigger for requests such as Create a user story; Write a user story; I need to write a user story. Part of cursor-rules-java project

日本語の概要は準備中です。原文の説明を表示しています。

aibot88/sec_skill_store42026年5月27日 更新

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. This should trigger for requests such as Create ADR for Non-functional requirements; Document Non-functional requirements; Capture Non-functional requirements; Generate Non-functional requirements in an ADR. Part of cursor-rules-java project

日本語の概要は準備中です。原文の説明を表示しています。

aibot88/sec_skill_store42026年5月27日 更新

Run a health check on an existing project: dependency audit, security scan, test runner detection, CI/CD evaluation, and missing configuration analysis. Maps the three execution gates (pre/in/post) from /10x-bootstrapper to an assessment framework for existing codebases. Reads optional context/foundation/stack-assessment.md from /10x-stack-assess to focus checks on identified gaps. Writes context/foundation/health-check.md with findings, prioritized fixes, and an agent-readiness verdict. Use when the user has an existing project and wants to verify its health before working with an agent. Trigger phrases: "health check", "check my project", "audit my project", "is my project healthy", "sprawdź projekt", "audyt projektu", "health-check", "project health". Use AFTER /10x-stack-assess (brownfield chain), BEFORE agent onboarding (m1-l4).

日本語の概要は準備中です。原文の説明を表示しています。

aibot88/sec_skill_store42026年5月27日 更新

10x-team

無料

You MUST use this when building projects end-to-end. Orchestrates all 12 team roles — automatically switches between CTO, architect, PM, engineers, SRE, security, DBA, QA, and EM based on the current phase of work. Starts with brainstorming before any implementation.

日本語の概要は準備中です。原文の説明を表示しています。

aibot88/sec_skill_store42026年5月27日 更新

Use when you need to add or configure Maven plugins in your pom.xml — including quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image build (Jib), build information tracking, and benchmarking (JMH) — through a consultative, modular step-by-step approach that only adds what you actually need. This should trigger for requests such as Add Maven plugins in pom.xml; Improve Maven plugins in pom.xml. Part of cursor-rules-java project

日本語の概要は準備中です。原文の説明を表示しています。

aibot88/sec_skill_store42026年5月27日 更新

aibot88 のスキルをすべて見る

このスキルの問題を報告する