Research Editor selected
Canary experiment exposes sensitive-data leaks across AI routing supply chain
Researcher HD Moore planted 2 million digital canaries in prompts routed through a sprawling network of AI services to trace how sensitive information leaks. The canaries included unused AWS keys, SSH passwords, unique URLs, DNS names, and private git repository references, each seeded into exactly one prompt sent to a single provider. The experiment found that the AI supply chain leaked highly sensitive data extensively, highlighting privacy and security risks in AI routers and gateways that broker prompts to inference providers.
Why it matters: It reveals concrete privacy and security risks in the increasingly common AI router/gateway layer that developers use to route prompts across model providers.
AI supply chain securityAI routersprivacy leakage