研究者向 AI 供应链投放 200 万个金丝雀密钥,发现敏感数据大规模泄露
研究者向 AI 供应链投放 200 万个金丝雀密钥,揭示敏感数据大规模泄露
研究者 HD Moore 向经 OpenRouter、Vercel 等 AI 网关转发的提示词中投放 200 万个从未使用过的金丝雀密钥,测试敏感信息是否会在 AI 服务链路中泄露,结果发现该生态大量泄露高敏感数据。他预先布好自控的 AWS 账户、SSH 凭据、DNS 与私有 git 引用等基础设施,每个密钥只放入一条发给单一提供商的提示词,任一凭据被触发即可定位泄露环节。
研究者用可追踪的金丝雀密钥定位 AI 路由链路中的泄露环节,为评估网关生态的隐私风险提供了可复用的实验方法。
Ars Technica:AI· Dan Goodin·2026-11-21 04:59· 2 小时前AI 评分65
Researcher plants 2m canaries into the AI supply chain. A privacy disaster surfaced.
AI 导读
研究者 HD Moore 向 AI 路由生态投放 200 万个从未使用过的金丝雀密钥,测试敏感信息是否会经 OpenRouter、Vercel 等 AI 网关链路泄露。他预先布好自控的 AWS 账户、SSH 凭据、DNS 与私有 git 引用等基础设施,任一凭据被触发即可定位泄露环节,结果发现该生态大量泄露高敏感数据。
正文 · 原文
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.
Security breaches, prompt theft, and privacy violations
To test for potential leakage, researcher HD Moore assembled a collection of AWS 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. None of the secrets had ever been used before, and he controlled the infrastructure that received any requests using the credentials. He then seeded each secret into exactly one prompt sent to a single provider. 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.
来源:Ars Technica:AI · arstechnica.com
来源:RadarAI · aihot.news