安全研究揭示低价 AI 推理服务商窃取密钥并窥探用户请求
Security researchers show how cheap AI inference providers steal keys and snoop on users
搞开发的朋友注意了,Dragos 用 200 万条假请求摸了一圈低价推理服务商,抓到 3 家被入侵的、好几百个 AWS 密钥被盗,还有转售商在偷看你的提示词。OpenRouter 已经下架 3 家服务商和 125 个端点。走聚合平台调模型的话,赶紧检查下自己的密钥权限。
Dragos 的安全研究人员用 200 万条伪造 AI 请求测试推理服务供应链,发现至少 3 家服务商已被入侵,数百个 AWS 密钥被盗。
部分市场转售商直接读取并查看客户的请求内容,用户提示词存在泄露风险。OpenRouter 在研究结果公布后移除了 3 家服务商和 125 个端点。
测试揭示了低价转售推理服务的商业模式中缺少安全审计环节:第三方转售商握有用户的 API 密钥和完整请求数据,却几乎没有监管约束。对通过聚合平台调用低价模型的开发者而言,API 密钥管理和提示词内容都可能暴露给不受信任的中间层,需要重新评估服务商信任链。
Security researchers show how cheap AI inference providers steal keys and snoop on users
Security researchers at Dragos used two million fake AI requests to uncover serious vulnerabilities in the AI supply chain, finding at least three compromised providers, hundreds of stolen AWS keys, and marketplace resellers who were simply reading customer requests. OpenRouter responded by removing three providers and 125 endpoints. The article Security researchers show how cheap AI inference providers steal keys and snoop on users appeared first on The Decoder .
This report is categorized under AITOP's "Industry" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include OpenRouter, AI safety, inference services, API keys.
Source attribution: curated from Decoder (@Matthias Bastian).