8.6
/ 10
HIGH
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:P
Description
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.
AI Analysis
Remote code execution vulnerability in RAGFlow due to untrusted data being parsed using eval() with no filtering or sandboxing, allowing low-privileged users to execute arbitrary system commands.
Basic Information
ID
CVE-2025-68700
Source
GitHub_M
Published
Dec 31, 2025 at 21:17
Affected Product
Vendor
infiniflow
Product
ragflow
Version
< 0.23.0
Affected Versions
infiniflow ragflow < 0.23.0
CWE Classification
AI Assessment
AI Score
8.6 / 10
AI Severity
High
Vendor
infiniflow
Product
RAGFlow
Version
< 0.23.0