Atlas / Skills / jeremylongshore / Deepgram Security Basics

Deepgram Security BasicsBLOCK

skills/jeremylongshore/deepgram-security-basics

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
BLOCK
Grade
D
Trust score
69 /100
Version
1.13.0
Hosts
1 documented
License
MIT
Stars
2,823
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: deepgram-security-basics
description: 'Apply Deepgram security best practices for API key management and data
  protection.

  Use when securing Deepgram integrations, implementing key rotation,

  or auditing security configurations.

  Trigger: "deepgram security", "deepgram API key security", "secure deepgram",

  "deepgram key rotation", "deepgram data protection", "deepgram PII redaction".

  '
allowed-tools: Read, Write, Edit, Grep, Bash(curl:*)
version: 1.13.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags:
- saas
- deepgram
- api
- security
- compliance
compatibility: Designed for Claude Code
---
# Deepgram Security Basics

## Prerequisites

- A data classification and consent decision for the audio/transcript workload.
- Scoped project credentials in the approved secret manager, an owner, and an incident/revocation route.

## Examples

Use a development credential and a licensed non-sensitive audio fixture to verify the integration, logging only an opaque request ID and outcome. If recordings, transcripts, or keys are exposed, restrict access, revoke credentials where applicable, and follow the organization’s incident process before continuing.

## Overview

Security best practices for Deepgram integration: scoped API keys, key rotation, Deepgram's built-in PII redaction feature, client-side temporary keys, SSRF prevention for audio URLs, and audit logging.

## Security Checklist

- [ ] API keys in environment variables or secret manager (never in code)
- [ ] Separate keys per environment (dev/staging/prod)
- [ ] Keys scoped to minimum required permissions
- [ ] Key rotation schedule (90 days recommended)
- [ ] Deepgram `redact` option enabled for PII-sensitive audio
- [ ] Audio URLs validated (HTTPS only, no private IPs)
- [ ] Audit logging on all transcription operations

## Instructions

### Step 1: Scoped API Keys

Create keys with minimal permissions in Console > Settings > API Keys:

```typescript
// Production transcription service — only needs listen scope
const sttKey = process.env.DEEPGRAM_STT_KEY;  // Scope: listen

// TTS service — only needs speak scope
const ttsKey = process.env.DEEPGRAM_TTS_KEY;  // Scope: speak

// Monitoring dashboard — only needs usage read
const monitorKey = process.env.DEEPGRAM_MONITOR_KEY;  // Scope: usage:read

// Admin operations — separate key, restricted access
const adminKey = process.env.DEEPGRAM_ADMIN_KEY;  // Scope: manage, keys
```

### Step 2: Deepgram Built-in PII Redaction

```typescript
import { createClient } from '@deepgram/sdk';

const deepgram = createClient(process.env.DEEPGRAM_API_KEY!);

// Deepgram redacts PII directly in the transcript
const { result } = await deepgram.listen.prerecorded.transcribeUrl(
  { url: audioUrl },
  {
    model: 'nova-3',
    smart_format: true,
    // Built-in redaction — replaces sensitive data in transcript
    redact: ['pci', 'ssn', 'numbers'],
    // pci     — Credit card numbers → [REDACTED]
    // ssn     — Social Security numbers → [REDACTED]
    // numbers — All numeric sequences → [REDACTED]
  }
);

// Transcript will contain [REDACTED] in place of sensitive numbers
console.log(result.results.channels[0].alternatives[0].transcript);
// "My card number is [REDACTED] and my SSN is [REDACTED]"
```

### Step 3: Temporary Keys for Client-Side

```typescript
// Generate short-lived keys for browser/mobile clients
// This prevents exposing your main API key

import { createClient } from '@deepgram/sdk';
import express from 'express';

const app = express();
const deepgram = createClient(process.env.DEEPGRAM_API_KEY!);

app.post('/api/deepgram/token', async (req, res) => {
  // Create a temporary key that expires in 10 seconds
  // Use for browser WebSocket connections
  const { result, error } = await deepgram.manage.createProjectKey(
    process.env.DEEPGRAM_PROJECT_ID!,
    {
      comment: `temp-key-${Date.now()}`,
      scopes: ['listen'],          // Minimal scope
      time_to_live_in_seconds: 10, // Short-lived
    }
  );

  if (error) return res.status(500).json({ error: error.message });
  res.json({ key: result.key, expires_in: 10 });
});

// Browser client uses temporary key:
// const { key } = await fetch('/api/deepgram/token').then(r => r.json());
// const ws = new WebSocket('wss://api.deepgram.com/v1/listen', ['token', key]);
```

### Step 4: Key Rotation

```typescript
import { createClient } from '@deepgram/sdk';

async function rotateApiKey(projectId: string) {
  const admin = createClient(process.env.DEEPGRAM_ADMIN_KEY!);

  // 1. Create new key with same scopes
  const { result: newKey } = await admin.manage.createProjectKey(projectId, {
    comment: `rotated-${new Date().toISOString().split('T')[0]}`,
    scopes: ['listen', 'speak'],
    expiration_date: new Date(Date.now() + 90 * 86400000).toISOString(), // 90 days
  });
  console.log('New key created:', newKey.key_id);

  // 2. Update secret manager (example: GCP Secret Manager)
  // await updateSecret('DEEPGRAM_API_KEY', newKey.key);

  // 3. Validate new key works
  const testClient = createClient(newKey.key);
  const { error } = await testClient.manage.getProjects();
  if (error) throw new Error('New key validation failed — aborting rotation');

  // 4. Delete old key (after services have picked up new key)
  // await admin.manage.deleteProjectKey(projectId, oldKeyId);

  return newKey;
}
```

### Step 5: Audio URL Validation (SSRF Prevention)

```typescript
import { URL } from 'url';
import { lookup } from 'dns/promises';

async function validateAudioUrl(url: string): Promise<void> {
  const parsed = new URL(url);

  // Require HTTPS
  if (parsed.protocol !== 'https:') {
    throw new Error('Only HTTPS audio URLs allowed');
  }

  // Block private/internal IPs
  const { address } = await lookup(parsed.hostname);
  const privateRanges = [
    /^127\./, /^10\./, /^172\.(1[6-9]|2\d|3[01])\./, /^192\.168\./,
    /^0\./, /^169\.254\./, /^::1$/, /^fc00:/, /^fe80:/,
  ];
  if (privateRange
04

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

HIGHNetwork egress · net.metadata_ip · CWE-200, CWE-319
SKILL.md:187
const blockedHosts = ['localhost', 'metadata.google.internal', '169.254.169.254'];
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
HIGHPrompt injection · prompt.credential_read · CWE-94, CWE-1427
SKILL.md:36
Use a development credential and a licensed non-sensitive audio fixture to verify the integration, logging only an opaque request ID and outcome. If recordings, transcripts, or keys are exposed, restr
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__deepgram-security-basics.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f83675ca38aBLOCKD69first audit
06

Questions

What does the Deepgram Security Basics skill do?

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Is Deepgram Security Basics safe to install?

No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What can Deepgram Security Basics access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does Deepgram Security Basics work with?

Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement