Simon Willison 博客T2·Tools
58 pts
Simon Willison's llm CLI tool released version 0.37.2, patching two security flaws that could leak the configured OpenAI API key to third-party OpenAI-compatible endpoints. The issues stem from the extra-openai-models.yaml mechanism, triggered when a named api_key_name was never stored or when a responses model was forced to use chat_completions.