CVE Tools

CVE-2025-69286

RAGFlow has Predictable Token Generation Leading to Authentication Bypass Vulnerability

No known exploitation. EPSS puts it in the 54th percentile. A vendor fix is available.

Published Updated Sources: CVE.org, NVD

What to do

The vendor has published a fix. Version details are below where the sources state them.

Steps

Written by AI from the record
  1. Check your RAGFlow version (look for the running version/build number in your deployment logs or the UI/config).
  2. If your version is older than 0.22.0, upgrade RAGFlow to 0.22.0 or later.
  3. Confirm whether you use “shared assistant/agent” links (beta share/auth features). If yes and you can’t upgrade immediately, temporarily disable sharing of assistant/agent links and rotate any generated keys/tokens you use for access.
  4. After upgrading, verify authentication still works as expected and that any previously issued shared links no longer grant access.

What it is

From the CVE record

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine. In versions prior to 0.22.0, the use of an insecure key generation algorithm in the API key and beta (assistant/agent share auth) token generation process allows these tokens to be mutually derivable. Specifically, both tokens are generated using the same `URLSafeTimedSerializer` with predictable inputs, enabling an unauthorized user who obtains the shared assistant/agent URL to derive the personal API key. This grants them full control over the assistant/agent owner's account. Version 0.22.0 fixes the issue.

In plain language

Written by AI from the record

CVE-2025-69286 is a serious RAGFlow token-guessing weakness that can let an attacker bypass logins and take over an assistant/agent account if they have the shared assistant/agent link; if you run RAGFlow and use those shared features, you should act now and upgrade to 0.22.0 or later.

In RAGFlow (versions before 0.22.0), predictable token generation (CWE-340) allows an attacker with access to the shared assistant/agent URL to derive the owner’s API key and bypass authentication, leading to full account takeover; exploitation is reported in the wild (actor: Qilin).

If you're affected

  • Full assistant/agent account takeover
  • Unauthorized API access
  • Data exposure from RAG workflows
  • Service disruption via abuse

Exploitation

Where each signal puts this CVE on the scale from published to confirmed exploited.

EPSS54th
CISA KEV

Not in the catalog. CISA has not confirmed exploitation.

Public exploits

No public exploit or proof of concept found in the sources we track.

EPSS

0.8% chance of exploitation activity in the next 30 days, which ranks it in the 54th percentile of scored CVEs.

Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.

Lifecycle

6 events over 266 days, from the signal feeds we watch.

  1. Patch availablerecord updated
  2. Patch availablerecord updated
  3. Publishedweakness classified

Affected products

Technical detail

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Scored 9.8 by NVD.

How it is reached

  • Attack Vector NetworkExploitable remotely over the network without any special conditions
  • Attack Complexity LowNo special conditions — the attack can be reliably reproduced
  • Privileges Required NoneNo authentication required — anyone can exploit this
  • User Interaction NoneNo user interaction needed — fully automated exploitation

Scope

  • Scope UnchangedImpact is limited to the vulnerable component itself

Impact if exploited

  • Confidentiality HighTotal information disclosure — all data in the component is compromised
  • Integrity HighTotal loss of integrity — attacker can modify any data in the component
  • Availability HighTotal denial of service — the component is completely unavailable

Weaknesses

Sources

Watch the software you run.

My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.

We'll flag the next CVE, public exploit or patch for Ragflow, not every advisory.

We use analytics cookies to see which pages and articles actually help people. Decline and none of them run — the site works the same. What we store