AI & Tech

Researcher plants 2m canaries into the AI supply chain. A privacy disaster surfaced.

In the event any of the secrets were leaked, these “canaries”—so called because they resemble the role of that bird when taken into coal mines—would allow Moore to identify each link in the chain that was responsible.

✦ Extractive summary — built from the sources' own reporting•From 1 source•1 min read•Updated November 20, 2026, 8:59 PM UTC
Key points
  • Security breaches, prompt theft, and privacy violations To test for potential leakage, researcher HD Moore assembled a collection of Amazon Web Services access keys, functioning credentials tied to empty AWS accounts, passwords for services such as SSH, and unique URLs, DNS names, and private git repository references.
  • Researchers planted 2 million digital tripwires in requests sent through a sprawling network of AI services to find out what happened to sensitive information entrusted to them.
  • None of the secrets had ever been used before, and he controlled the infrastructure that received any requests using the credentials.

The exposure was found through an ingenious experiment designed to test if sensitive information can leak through the vast chain of widely used AI services and how that information is exploited when it does.

Additional details
  • Instead of using Anthropic, OpenAI, or another big provider, the developer hires an AI router to find the most suitable model.
  • Many of today’s AI apps use services such as OpenRouter or Vercel that act as brokers.
  • What they discovered was an ecosystem that leaked highly sensitive data like a sieve.
  • He then seeded each secret into exactly one prompt sent to a single provider.

How this summary was made: extractive summary — built from the sources' own reporting. It is drawn only from the reporting of the sources listed below — read the originals for full detail. How we summarize →

Advertisement

Every article behind this summary — 1 article from 1 outlet