返回全部资讯
Simon Willison 博客T2·开发与工程

llm 0.37.2 修复 API 密钥泄露漏洞

原标题:llm 0.37.2
58AI 研判分

Simon Willison 的 llm 命令行工具发布 0.37.2 版本,修复了两个可能导致 OpenAI API 密钥被意外发送给第三方兼容端点的安全漏洞。漏洞源于 extra-openai-models.yaml 配置机制:当 api_key_name 指定的密钥从未存储,或对 responses 模型强制使用 chat_completions 时,密钥可能被泄露。

报道正文

Fixes a security issue reported by Daniel de Araujo in GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w.

LLM has a mechanism called extra-openai-models.yaml - now managed by the new-in-0.37 llm openai endpoint add command - for using LLM with OpenAI-compatible API endpoints from other providers.

Daniel reported two ways this could accidentally send your configured OpenAI API key to one of those providers: if the key named by api_key_name had never been stored, or if a responses: true model was run with -o chat_completions 1.