CVE-2025-68700: RAGFlow Remote Code Execution Vulnerability
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. In versions prior to 0.23.0, a low-privileged authenticated user (normal login account) can execute arbitrary system commands on the server host process via the frontend Canvas CodeExec component, completely bypassing sandbox isolation. This occurs because untrusted data (stdout) is parsed using eval() with no filtering or sandboxing. The intended design was to "automatically convert string results into Python objects," but this effectively executes attacker-controlled code. Additional endpoints lack access control or contain inverted permission logic, significantly expanding the attack surface and enabling chained exploitation. Version 0.23.0 contains a patch for the issue.
Affected Software
Remediation
Event History
Frequently Asked Questions
What is the severity of CVE-2025-68700?
CVE-2025-68700 is classified as a high severity vulnerability due to its potential for arbitrary command execution.
How do I fix CVE-2025-68700?
To mitigate CVE-2025-68700, upgrade RAGFlow to version 0.23.0 or later, where the vulnerability has been addressed.
Who is affected by CVE-2025-68700?
Users of RAGFlow versions prior to 0.23.0 are vulnerable to CVE-2025-68700.
What is the exploit vector for CVE-2025-68700?
CVE-2025-68700 can be exploited by low-privileged authenticated users through the Canvas CodeExec component.
What type of vulnerability is CVE-2025-68700?
CVE-2025-68700 is a command injection vulnerability allowing execution of arbitrary system commands.