How I Simulated a Supply Chain Attack on Thousands of Servers — and Made $25K
嗯,用户让我总结一下这篇文章的内容,控制在一百个字以内,而且不需要用“文章内容总结”之类的开头。首先,我需要通读整篇文章,抓住主要信息。 文章讲的是作者发现一个被遗弃的Google Cloud Storage桶,里面曾用于分发Helm二进制文件。他通过GitHub搜索发现很多项目还在引用这个桶。于是他开始报告问题,得到一些赏金。后来他更进一步,启用访问日志,发现很多系统还在使用这个桶下载二进制文件。于是他模拟供应链攻击,生成包含恶意负载的二进制文件,收集了大量系统信息,并通过赏金计划获得了约2.5万美元的奖励。最后Google接管了这个桶,消除了风险。 接下来我要把这些要点浓缩到100字以内。要包括发现旧存储桶、GitHub上的引用、启用日志、模拟攻击、收集数据、赏金、Google接管和消除风险。 可能的结构是:作者发现旧存储桶被广泛引用,启用日志后发现大量使用,模拟攻击收集数据并获得赏金,最终Google接管消除了风险。 检查字数是否在限制内,并确保没有使用不需要的开头。 </think> 作者发现一个被遗弃的Google Cloud Storage存储桶被广泛引用,在启用访问日志后发现大量系统仍在使用该桶下载二进制文件。通过模拟供应链攻击收集数据并报告漏洞,最终获得约2.5万美元赏金,并促使Google接管存储桶以消除风险。 2026-4-4 10:33:43 Author: infosecwriteups.com(查看原文) 阅读量:10 收藏

Arshad Kazmi

While hunting for broken link takeover opportunities, I came across an old Google Cloud Storage bucket that was previously used for Helm binary distribution. The bucket was no longer owned, but references to it still existed across the ecosystem.

Out of curiosity, I searched GitHub and quickly found thousands of repositories still referencing this bucket in CI pipelines, Dockerfiles, and deployment scripts.

At this stage, I started reporting the issue directly to programs where I could clearly see usage in their GitHub repositories. Since the references were public, it was straightforward to demonstrate potential impact.

I received some initial bounties from these reports. You can check the writeup here — How I Took Over a Forgotten Google Storage Bucket Used to Distribute Helm Binaries.

However, this approach felt limited — I was only reporting based on visible references, not actual live usage.

That’s when I decided to take a different approach.

Instead of continuing with static findings, I enabled access logging on the bucket and started monitoring real traffic.

Within a few days, I started seeing thousands of requests daily from a wide range of servers. This confirmed that many systems were still actively pulling binaries from this location.

That’s when the real idea clicked.

If these systems were blindly downloading binaries, I could simulate a supply chain attack.

Using AI (Cursor), I generated a script that:

  • Recreated Helm binary archives matching the original naming patterns
  • Covered multiple OS/architecture combinations and versions
  • Injected a small bash payload inside each archive

The payload was simple:

  • Collect non-sensitive system information (hostname, IP, whoami, cwd)
  • Send it to my controlled webhook

On the backend, I again used AI to quickly set up:

  • A webhook receiver
  • Database storage
  • WHOIS lookup for incoming IPs
  • A basic UI to visualize incoming data

The entire pipeline was ready in minutes.

As soon as I started uploading the crafted binaries to the bucket, I began receiving hits — even before the upload completed.

Within a week, I was seeing:

  • ~1,000+ requests per day
  • Thousands of unique machines
  • Continuous traffic from production environments

This clearly showed real-world impact at scale.

Get Arshad Kazmi’s stories in your inbox

Join Medium for free to get updates from this writer.

Remember me for faster sign in

One major challenge was attribution.

Most IPs resolved to cloud providers like AWS, GCP, and others, which made it difficult to identify the actual organization behind them.

To improve signal, I:

  • Filtered out generic cloud IP ranges
  • Focused only on IPs with identifiable ownership

This helped surface traffic from recognizable organizations.

I began reporting affected companies through their bug bounty programs.

Responses varied:

  • Some marked it as informational (test or isolated systems)
  • Some acknowledged but rated it low
  • Others treated it as a critical supply chain risk

Over time, I received multiple bounties:

  • Several private program rewards on HackerOne
  • Additional payouts: $3K, $1K, $500, $100
  • Some reports are still pending

Press enter or click to view image in full size

Bounty from Google

A few days later, I noticed traffic from an Apple-owned server.

That was a big moment.

I reported it immediately. Apple took it seriously and began internal investigation. Eventually, they coordinated with Google and concluded that the best fix was to secure the bucket itself.

There was even discussion around ownership transfer.

In the end:

  • Google took over the bucket
  • The supply chain risk was neutralized at the root

Final numbers:

  • Total earnings: ~$25,000
  • Highest single bounty: $15,000 (Apple)
  • Impact: Thousands of machines across multiple organizations

This could have gone even further if the bucket had remained unclaimed a bit longer 😉

Press enter or click to view image in full size

15k Bounty from Apple

文章来源: https://infosecwriteups.com/how-i-simulated-a-supply-chain-attack-on-thousands-of-servers-and-made-25k-7d36647cbf36?source=rss----7b722bfd1b8d--bug_bounty
如有侵权请联系:admin#unsafe.sh