Assemblyai security basics
425 plugins, 2,810 skills, 200 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.
npx -y skills add jeremylongshore/claude-code-plugins-plus-skills --skill assemblyai-security-basicsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
'Apply AssemblyAI security best practices for API keys, PII, and access control.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
5.9 KB, as published. Nobody here has run it
AssemblyAI Security Basics
Overview
Security best practices for AssemblyAI: API key management, temporary tokens for browser clients, PII redaction, and data retention policies.
Prerequisites
assemblyaipackage installed- Understanding of environment variables
- AssemblyAI dashboard access
Instructions
Step 1: API Key Management
# .env (NEVER commit)
ASSEMBLYAI_API_KEY=your-api-key-here
# .gitignore
.env
.env.local
.env.*.local
// Never hardcode API keys
// BAD:
const client = new AssemblyAI({ apiKey: 'sk_abc123...' });
// GOOD:
import { AssemblyAI } from 'assemblyai';
const client = new AssemblyAI({
apiKey: process.env.ASSEMBLYAI_API_KEY!,
});
Step 2: Temporary Tokens for Browser Streaming
Never expose your API key in frontend code. Use temporary tokens for browser-side streaming:
// Server-side: /api/assemblyai-token.ts
import { AssemblyAI } from 'assemblyai';
const client = new AssemblyAI({
apiKey: process.env.ASSEMBLYAI_API_KEY!,
});
export async function GET() {
// Token expires after 5 minutes
const token = await client.streaming.createTemporaryToken({
expires_in_seconds: 300,
});
return Response.json({ token });
}
// Client-side: use the temporary token
// const { token } = await fetch('/api/assemblyai-token').then(r => r.json());
// const transcriber = new StreamingTranscriber({ token });
Step 3: PII Redaction in Transcripts
const transcript = await client.transcripts.transcribe({
audio: audioUrl,
redact_pii: true,
redact_pii_policies: [
'email_address',
'phone_number',
'person_name',
'credit_card_number',
'social_security_number',
'date_of_birth',
'medical_condition',
'banking_information',
'us_social_security_number',
],
redact_pii_sub: 'entity_name', // or 'hash'
// 'entity_name': "My name is [PERSON_NAME]"
// 'hash': "My name is ####"
});
// Also redact the audio itself
const transcriptWithRedactedAudio = await client.transcripts.transcribe({
audio: audioUrl,
redact_pii: true,
redact_pii_policies: ['person_name', 'phone_number'],
redact_pii_audio: true, // Generates audio with PII beeped out
});
Step 4: Data Retention and Deletion
// Delete transcript data for GDPR/privacy compliance
await client.transcripts.delete(transcriptId);
// This permanently removes the transcript text and metadata
// The audio file at your source URL is NOT deleted (you manage that)
// List and bulk-delete old transcripts
const page = await client.transcripts.list({ limit: 100 });
for (const t of page.transcripts) {
const createdDate = new Date(t.created);
const daysOld = (Date.now() - createdDate.getTime()) / (1000 * 60 * 60 * 24);
if (daysOld > 30) {
await client.transcripts.delete(t.id);
console.log(`Deleted transcript ${t.id} (${daysOld.toFixed(0)} days old)`);
}
}
Step 5: Content Safety Detection
// Detect sensitive content before it reaches your users
const transcript = await client.transcripts.transcribe({
audio: audioUrl,
content_safety: true,
});
const safetyResults = transcript.content_safety_labels?.results ?? [];
for (const result of safetyResults) {
for (const label of result.labels) {
if (label.confidence > 0.8) {
console.warn(`Content safety flag: ${label.label} (${(label.confidence * 100).toFixed(0)}%)`);
// Labels include: hate_speech, violence, profanity, etc.
}
}
}
// Get overall severity summary
const summary = transcript.content_safety_labels?.summary ?? {};
for (const [category, severity] of Object.entries(summary)) {
console.log(`${category}: severity ${severity}`);
}
Step 6: Security Checklist
- API key stored in environment variable, never in code
-
.envfiles listed in.gitignore - Separate API keys for dev/staging/prod environments
- Temporary tokens used for browser streaming (not raw API key)
- PII redaction enabled for sensitive audio
- Old transcripts deleted per retention policy
- Content safety enabled for user-generated audio
- Webhook endpoints validate payload authenticity
- CI/CD secrets stored in platform secrets manager (not env files)
Output
- Secure API key storage pattern
- Temporary token endpoint for browser streaming
- PII redaction with configurable policies
- Data retention automation
- Content safety detection
Error Handling
| Security Issue | Detection | Mitigation |
|---|---|---|
| API key in source code | Git scanning / secrets detection | Rotate key immediately at dashboard |
| API key in browser JS | Network tab inspection | Use temporary tokens |
| PII in transcripts | Manual review or automated scan | Enable redact_pii |
| Old transcripts retained | Audit transcript list | Automate deletion schedule |
Resources
Next Steps
For production deployment, see assemblyai-prod-checklist.