CyberRota Analysis
AI-GeneratedLaVague 0.2.35 is vulnerable to a remote code execution flaw that allows attackers to inject malicious Python code via web pages, exploiting the PythonFromMarkdownExtractor.extract_as_object function. This vulnerability enables the execution of arbitrary code on the operator's host without prior review of the injected content. Organizations using this version of LaVague should prioritize immediate remediation to mitigate the risk of exploitation.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extract_as_object that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute arbitrary code on the operator's host without review.