DEV Community

Cover image for Auditing unsafe passwords
Karan Pratap Singh
Karan Pratap Singh

Posted on

Auditing unsafe passwords

In this article, we'll look at how we can setup our own infrastructure for auditing passwords using haveibeenpwned list of compromised passwords.

Why do we need this?

While password auditing is not the most important thing, it can be still be quite helpful in improving our user's security as follows:

  • Users will have to create stronger passwords that aren't leaked in public data breach when they signup for our services.
  • We can create a cron job to asynchronously audit passwords of early users and suggest them to update their password.

Download and Extract

You can download it either as a torrent or directly from here

$ mkdir hibp
$ cd hibp
$ wget
$ 7za x pwned-passwords-sha1-ordered-by-count-v7.7z
Enter fullscreen mode Exit fullscreen mode

Let's see how many passwords pwned-passwords-sha1-ordered-by-count-v7.txt file contains.

$ wc -l chunks/pwned-passwords-sha1-ordered-by-hash-v7.txt
Enter fullscreen mode Exit fullscreen mode

That's over 600M compromised passwords!

Note: I will recommend to do this on EC2, something like t3.2xlarge which has 8 vCPUs and 5 Gbps network bandwidth for us to play with.

Pre-process data

While, the password list is about ~26 GB in size which is not huge, but it has over 600M records!

So, we need to pre-process it by splitting in to smaller chunks of 1M records each, which are much easier to process.

$ mkdir chunks
$ cd chunks
$ split -l 1000000 ../pwned-passwords-sha1-ordered-by-hash-v7.txt chunk-
Enter fullscreen mode Exit fullscreen mode

This should create 600 chunks of the original file like this:

$ ls chunks
Enter fullscreen mode Exit fullscreen mode


For storage, we have various different options:

I'll be using DynamoDB for storage, as I think it's perfect for this usecase. Let's provision our DynamoDB table with terraform and create an attribute hash for indexing:

resource "aws_dynamodb_table" "hibp_table" {
  name           = "Hibp"
  billing_mode   = "PROVISIONED"
  read_capacity  = 5
  write_capacity = 1

  hash_key = "hash"

  attribute {
    name = "hash"
    type = "S"
Enter fullscreen mode Exit fullscreen mode

Note: If you're not familiar with Terraform, feel free to checkout my earlier post on it.


Before we start playing with the data, Let's look at different options we have to write the data to our DynamoDB table:

As this was a one off thing for me, I simply created a script to utilize BatchWriteItem API to get the data to the DynamoDB table. If you already using data pipeline or EMR, feel free to do that as it might be better in the long run? That's a question better left to our friends doing data engineering!


But wait...this was more tricky than I thought. My initial plan was to make a script with JavaScript to batch write 1M records at a time. Unfortunately, BatchWriteItem API only allows 25 items per batch request, maybe for a good reason?.

We have hope!

We need multi-threading or something similar! For this I choose Golang, I love how lightweight and powerful goroutines are! So, here's our new approach:

  • Transform

Chunks we created earlier for pwned-passwords-sha1-ordered-by-count-v7.txt are in a format like:

<SHA-1>:<no of times compromised>
Enter fullscreen mode Exit fullscreen mode

Note: The SHA-1 is already in uppercase to reduce query time as per the author of the file.

So basically, bigger the number on the right, worse the password. This is the rough schema we'll be using for our DynamoDB table:

Column        |       Type
hash (index)  |         S
times         |         N
type          |         S
Enter fullscreen mode Exit fullscreen mode

Note: We included the type field to store which type of algorithm the hash is using, right now we'll store SHA-1 but in the future we can extend and filter our table with other password lists.

We can now simply iterate over the all the contents and transform them into 1M million batch write requests like we originally intended to.

  • Chunking

Since we know that we cannot exceed 25 items per batch write request, let's break our 1M requests in to 40K chunks to not exceed limits from AWS.

  • Batching

Now, let's further break our 40K chunks into 4 batches of 10K each. Finally, we can iterate over these 4 batches and launch 10K goroutines each time. Hence, every iteration we "theoritically" write 250k records to our table.

Let's Code

Here's our ideas in Golang. Let's init our module and add aws-sdk.

Note: All the code is also available in this repository

$ go mod init ingest
$ touch main.go
Enter fullscreen mode Exit fullscreen mode

Create our job.log file

$ mkdir logs
$ touch logs/job.log
Enter fullscreen mode Exit fullscreen mode

This should give us a structure like this:

├── chunks
│   └── ...
├── logs
│   └── job.log
├── go.mod
├── go.sum
└── main.go
Enter fullscreen mode Exit fullscreen mode

Let's add content to our main.go file.

package main

import (

    dynamodbTypes ""

type Schema struct {
    Hash  string `dynamodbav:"hash"`
    Times int    `dynamodbav:"times"`
    Type  string `dynamodbav:"type"`

var table string = "Hibp"
var dir string = "chunks"

func main() {
    logFile, writer := getLogFile()
    defer logFile.Close()

    log.Println("Using table", table, "with directory", dir)

    files := getFiles(dir)

    for num, file := range files {
        filename := file.Name()
        path := "chunks/" + filename

        log.Println("====", num+1, "====")
        log.Println("Starting:", filename)

        file, err := os.Open(path)

        if err != nil {

        defer file.Close()

        scanner := bufio.NewScanner(file)

        items := []dynamodbTypes.WriteRequest{}

        for scanner.Scan() {
            line := scanner.Text()

            schema := parseLine(line)
            attribute := getAttributes(schema)

            item := dynamodbTypes.WriteRequest{
                PutRequest: &dynamodbTypes.PutRequest{
                    Item: attribute,

            items = append(items, item)

        chunks := createChunks(items)
        batches := createBatches(chunks)

        log.Println("Created", len(batches), "batches for", len(chunks), "chunks with", len(items), "items")

        var wg sync.WaitGroup

        for index, batch := range batches {
            failed := 0
            log.Println("Processing batch", index+1)
            batchWriteToDB(&wg, batch, &failed)
            log.Println("Completed with", failed, "failures")

        log.Println("Processed", filename)

        if err := scanner.Err(); err != nil {


func getLogFile() (*os.File, io.Writer) {
    file, err := os.OpenFile("logs/job.log", os.O_RDWR|os.O_CREATE|os.O_APPEND, 0666)
    if err != nil {
        log.Fatalf("error opening file: %v", err)

    mw := io.MultiWriter(os.Stdout, file)

    return file, mw

func getDynamoDBClient() dynamodb.Client {
    cfg, err := config.LoadDefaultConfig(context.TODO(), config.WithRetryer(func() aws.Retryer {
        return retry.AddWithMaxAttempts(retry.NewStandard(), 5000)

    cfg.Region = "us-west-2"

    if err != nil {

    return *dynamodb.NewFromConfig(cfg)

func getFiles(dir string) []fs.FileInfo {
    files, dirReadErr := ioutil.ReadDir("chunks")

    if dirReadErr != nil {

    return files

func parseLine(line string) Schema {
    split := strings.Split(line, ":")

    Hash := split[0]
    Times, _ := strconv.Atoi(split[1])
    Type := "SHA-1"

    return Schema{Hash, Times, Type}

func getAttributes(schema Schema) map[string]dynamodbTypes.AttributeValue {
    attribute, err := attributevalue.MarshalMap(schema)

    if err != nil {
        log.Println("Error processing:", schema)

    return attribute

func batchWriteToDB(wg *sync.WaitGroup, data [][]dynamodbTypes.WriteRequest, failed *int) {
    for _, chunk := range data {

        go func(chunk []dynamodbTypes.WriteRequest, failed *int) {
            defer wg.Done()
            client := getDynamoDBClient()

            _, err := client.BatchWriteItem(context.TODO(), &dynamodb.BatchWriteItemInput{
                RequestItems: map[string][]dynamodbTypes.WriteRequest{
                    table: chunk,

            if err != nil {
                *failed += 1
        }(chunk, failed)

func createChunks(arr []dynamodbTypes.WriteRequest) [][]dynamodbTypes.WriteRequest {
    var chunks [][]dynamodbTypes.WriteRequest
    var size int = 25

    for i := 0; i < len(arr); i += size {
        end := i + size

        if end > len(arr) {
            end = len(arr)

        chunks = append(chunks, arr[i:end])

    return chunks

func createBatches(arr [][]dynamodbTypes.WriteRequest) [][][]dynamodbTypes.WriteRequest {
    var batches [][][]dynamodbTypes.WriteRequest
    var size int = 10000

    for i := 0; i < len(arr); i += size {
        end := i + size

        if end > len(arr) {
            end = len(arr)

        batches = append(batches, arr[i:end])

    return batches
Enter fullscreen mode Exit fullscreen mode

Now, we need to go update our write capacity to 30k so the table can handle the load from our script.

We're provisioning 30k write capacity which is almost $15k a month! Although we will only use this capacity for just few hrs, it is easy to forget to scale it down afterwards. Make sure to create a billing alert for $100, so you don't forget. Please don't blame me if you get a huge bill from AWS next month.


$ go build main.go
$ ./main

==== 1 ====
2021/10/22 16:18:25 Starting: chunk-ix
2021/10/22 16:18:28 Created 4 batches for 40000 chunks with 1000000 items
2021/10/22 16:18:28 Processing batch 1
2021/10/22 16:18:28 Completed with 0 failures
2021/10/22 16:18:33 Processing batch 2
2021/10/22 16:18:33 Completed with 0 failures
2021/10/22 16:18:39 Processing batch 3
2021/10/22 16:18:39 Completed with 0 failures
2021/10/22 16:18:44 Processing batch 4
2021/10/22 16:18:45 Completed with 0 failures
Enter fullscreen mode Exit fullscreen mode

Image description


Benchmarks are for 1M records with t3.2xlarge. Here, Golang performs way faster when compared to JavaScript due to goroutines utilizing all the thread, plus it's faster in general.

JavaScript (Node.js 16)
~1083s (~18 minutes)

Go (1.17)
Enter fullscreen mode Exit fullscreen mode

So, to conclude we can finish the whole thing in 3-4 hrs with Go!


Now since we have our table setup, we can simply query like below:

import { DynamoDB } from 'aws-sdk';
import crypto from 'crypto';

const client = new AWS.DynamoDB();
const TableName = 'Hibp';

type UnsafeCheckResult = {
  unsafe: boolean;
  times?: number;

export async function unsafePasswordCheck(password: string): Promise<UnsafeCheckResult> {
  const shasum = crypto.createHash('sha1').update(password);
  const hash = shasum.digest('hex').toUpperCase();

  const params: DynamoDB.QueryInput = {
    KeyConditionExpression: '#hash = :hash',
    ExpressionAttributeNames: {
      '#hash': 'hash',
    ExpressionAttributeValues: {
      ':hash': { S: hash },

  const result: DynamoDB.QueryOutput = await dynamoDbClient

  if (result?.Count && result?.Items?.[0]) {
    const [document] = result.Items;
    const foundItem = DynamoDB.Converter.unmarshall(document);

    return { unsafe: true, times: foundItem?.times };

  return { unsafe: false };
Enter fullscreen mode Exit fullscreen mode

Cost estimation

DynamoDB: 30k write capacity ($14251.08/month or $19.50/hr)
EC2: t3.2xlarge ($0.3328/hr)

Duration: ~4hrs

Total: $19.8328 * 4hrs = ~$79.3312
Enter fullscreen mode Exit fullscreen mode

The main component in price is the DynamoDB's 30k write capacity, if we can use a better EC2 machine (let's say c6g.16xlarge) and launch more goroutines to utilise additional write capacity (let's say 40k). It will be more expensive but it might reduce total time we took. This will reduce the DynamoDB usage, reducing the overall price under $60!

Perfomance improvements?

Are your queries too slow? Do you have millions of users? To improve query performance, we can setup bloom filters with redis to reduce load the DB.


I hope this was helpful, feel free to reach out to me on twitter if you face any issues. Thanks for reading!

Discussion (4)

mikestaub profile image
Mike Staub

Nice post!

karanpratapsingh profile image
Karan Pratap Singh Author

Thanks Michael!

karandpr profile image
Karan Gandhi

Probably overkill for most scenarios but still cool thing to do,.

karanpratapsingh profile image
Karan Pratap Singh Author

yeah haha, but can be quite handy in high compliance industries