CVE-2026-119337

RAGFlow: OpenAI-compatible agent completion bypasses private canvas authorization

Published Oct 30, 2026 CVSS 3.1 · 7.1 High EPSS < 1% KEV · Not listed
Description
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. From 0.25.2 until 0.27.3, POST /api/v1/agents/chat/completions invokes completion_openai and returns through the openai-compatible branch before UserCanvasService.accessible() checks whether the caller may access the requested agent. An authenticated user who knows another user's private agent UUID can execute that Only me workflow and read its output across the user or tenant boundary; configured tools may also cause side effects, but stronger impacts were not demonstrated. This issue is fixed in version 0.27.3.

Analysis

AI-generated

Technical impact

RAGFlow, an open‑source Retrieval‑Augmented Generation engine, contains a flaw that allows an authenticated user to invoke an OpenAI‑compatible completion endpoint for a private agent. This is a CWE-862 vulnerability, representing an authorization bypass through privileged attribute. The POST /api/v1/agents/chat/completions route returns the result from the openai‑compatible branch before the UserCanvasService.accessible() check runs, enabling the caller to read a private agent’s output even when the agent is configured as "Only me". The impact is the disclosure of private agent responses and, potentially, execution of configured tools that may have side effects, leading to confidentiality and integrity violations across tenant boundaries.

Affected Systems

The vulnerability affects Infiniflow RAGFlow versions from 0.25.2 up to and including 0.27.3. Any deployment using these versions is at risk unless updated.

Risk and Exploitability

The CVSS base score is 7.1, indicating high severity. EPSS information is not available, and the vulnerability is not listed in CISA's KEV catalog. The likely attack vector requires a legitimate authenticated user who knows the UUID of another user's private agent. The attack does not require elevation to administrative privileges, but it does allow an attacker to bypass authorization checks and access cross‑tenant data.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade Infiniflow RAGFlow to version 0.27.3 or later to incorporate the authorization check before completion.
  • After upgrading, audit your configuration to ensure that agent UUIDs are not exposed in public logs or user‑facing interfaces, preventing attackers from guessing or enumerating private agent IDs.
  • Review any configured tools used by agents, disable or restrict those that can perform privileged actions, and enforce strict access controls to mitigate potential side‑effect exploitation.

Generated by OpenCVE AI on October 30, 2026 at 22:09 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Infiniflow
Infiniflow ragflow
Vendors & Products Infiniflow
Infiniflow ragflow
Type Values Removed Values Added
Description RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. From 0.25.2 until 0.27.3, POST /api/v1/agents/chat/completions invokes completion_openai and returns through the openai-compatible branch before UserCanvasService.accessible() checks whether the caller may access the requested agent. An authenticated user who knows another user's private agent UUID can execute that Only me workflow and read its output across the user or tenant boundary; configured tools may also cause side effects, but stronger impacts were not demonstrated. This issue is fixed in version 0.27.3.
Title RAGFlow: OpenAI-compatible agent completion bypasses private canvas authorization
Weaknesses CWE-862
References
Metrics cvssV3_1

{'score': 7.1, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N'}

Weaknesses

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Nov 6, 2026, 6:04 PM
Reserved
Oct 29, 2026, 8:44 PM
Status
Deferred
Published
Oct 30, 2026, 8:17 PM
Modified
Nov 6, 2026, 7:17 PM