WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, there is a command injection vulner…

WeKnora, an LLM-powered framework for document understanding and semantic retrieval, contains a command injection vulnerability in versions prior to 0.2.5. The vulnerability allows authenticated users to inject malicious commands into stdio_config.command/args within MCP stdio settings. This enables attackers to execute arbitrary subprocesses on the server using the injected values. The security issue affects the framework's ability to safely handle user input in configuration settings. Tencent has addressed this vulnerability by releasing a patch in version 0.2.5. Users are advised to upgrade to the latest version to mitigate the command injection risk.