SUMMARYResearchers tested a network of AI routing services by embedding millions of unique canary secrets into prompts and tracking where those credentials surfaced. The experiment found that sensitive data such as AWS keys, passwords, and private repository references could leak through the AI supply chain, exposing privacy and security weaknesses in commonly used AI brokers and gateways.
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. What they discovered was an ecosystem that leaked highly sensitive data like a sieve.
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. Many of today’s AI apps use services such as OpenRouter or Vercel that act as brokers. These “AI routers,” sometimes also known as “AI gateways,” receive large numbers of prompts sent from AI app end users and route them to an available inference engine based on criteria such as the one charging the lowest price or being best suited for the given task. Instead of using Anthropic, OpenAI, or another big provider, the developer hires an AI router to find the most suitable model.
Update, Nov 21: Posts on both Hacker News and X report that OpenRouter has sent customers an email notifying them that some of their prompts may have been read. OpenRouter cited the research and said that it received a report that the potential exposure involved prompts sent to MiniMax, a China-based model provider. OpenRouter said the researchers' planted URLs were accessed whether the prompts were sent to MiniMax directly or through three other resellers: AtlasCloud, Novita, and StreamLake. OpenRouter has removed a "Zero Data Retention" label from MiniMax-model endpoints. Hat tip: Sulat.com.
