Hacking Google with AI for $500,000

From the article:

Having spent the past year building small projects with Claude, I realized there was untapped potential in using AI to automatically fuzz Google's APIs at scale. The key to this approach? Google's discovery documents. For those unfamiliar, I'd recommend reading my other article for a deep dive, but here's a quick refresher:

Discovery documents are essentially Google's equivalent of Swagger docs - machine-readable API specifications that list all available endpoints, parameters, and methods. While they're publicly documented for APIs like the YouTube Data API, they also exist for Google's internal APIs (like the Internal People API). Some discovery docs are publicly accessible, while most require valid API keys.

[...]

We took an exhaustive approach. We scraped over 60,000 Android APKs (every version of every Google app ever released), unpacked them, and grepped for API keys.

[...]

We also decrypted every Google IPA we could obtain and analyzed any Google binaries we could find.

To keep things in scope for Google VRP and remove non-Google API keys (keys from third-party GCP projects), I used an interesting endpoint I found in the Cloud Marketplace API. First, we need the project number associated with the key's GCP project, which is revealed in the error message returned when using the key with a Google API it doesn't have enabled. For instance, fetching https://protos.googleapis.com/$discovery/rest?key=AIzaSyDWUi9T78xEO-m10evQANR7TMSiB_bjyNc returns the error: Protos API has not been used in project 244648151629 before, revealing the project number.

[...]

With API keys collected, the next step was finding all Google API domains to scan. I used a combination of domains logged by the Chrome extension, brute-force generated names using keywords, and certificate transparency logs. To verify if a domain was a live Google API, I made the following request:

[...]

Equipped with valid API keys and a list of live Google API domains, I started mass scanning for open discovery documents. In July 2025, Google removed the /$discovery/rest path from most of their APIs, but if you're clever enough this is possible to bypass in some cases.

[...]

It was now time to start automatically fuzzing these APIs. My goal was to automate finding basic access control issues, which I could then escalate manually into more serious vulnerabilities. In fact, the RCE I found in my previous writeup was initially a lead reported by the AI.

[...]

Three months of this setup turned up over $500,000 in bounties, only a fraction of which made it here. Most Google bugs don't need clever exploitation, just patience. The same broken patterns showed up everywhere: missing IAM checks on cross-tenant resources, GraphQL schemas with no authorization, debug endpoints in prod, sandbox environments pointing at prod data. The AI's job wasn't to be novel, it was to be tireless about the obvious on a surface too large for a human to cover end-to-end.