在检索增强生成(RAG)过程中过滤文档时,auth0-ai-python 的 FGA 检索器未能区分不同用户、关系或条件下的授权检查,导致本应被 Auth0 FGA 拒绝访问的文档被纳入模型上下文,并用于生成响应。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| Auth0 | auth0-ai-langchain | 0 ~ 1.0.2 | - |
|
| Auth0 | auth0-ai-llamaindex | 0 ~ 1.0.3 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-107372 | auth0-ai-js FGA检索器权限绕过漏洞 | |
| CVE-2026-126129 | Auth0 SDK 错误处理 OIDC 注销导致未授权访问 | |
| CVE-2026-126128 | Auth0 Node.js SDK 路径参数处理不当导致越权访问 |