CVE-2025-69985
Authentication Bypass in FUXA JWT Middleware Enables RCE
Publication date: 2026-02-24
Last updated on: 2026-02-26
Assigner: MITRE
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| frangoteam | fuxa | to 1.2.8 (inc) |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-288 | The product requires authentication, but the product has an alternate path or channel that does not require authentication. |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
[{'type': 'paragraph', 'content': "CVE-2025-69985 is a vulnerability in FUXA version 1.2.8 and prior that allows an unauthenticated attacker to bypass authentication by exploiting an improper trust of the HTTP Referer header in the server's jwt-helper.js middleware."}, {'type': 'paragraph', 'content': 'The vulnerability occurs because the system\'s authentication middleware whitelists requests based on the Referer header containing "/fuxa", allowing attackers to spoof this header to appear as an internal request.'}, {'type': 'paragraph', 'content': 'This bypass enables the attacker to access the protected /api/runscript endpoint and execute arbitrary Node.js code on the server, leading to Remote Code Execution (RCE).'}, {'type': 'paragraph', 'content': 'Additionally, attackers can exploit this to overwrite the user database with a malicious SQLite3 database, effectively taking over admin accounts by setting a known password.'}] [1]
How can this vulnerability impact me? :
This vulnerability can have severe impacts including unauthorized remote code execution on the server hosting FUXA, which can lead to full system compromise.
An attacker can execute arbitrary Node.js code, potentially running malicious commands or software on the server.
Furthermore, the attacker can overwrite the user database to create or take over admin accounts, granting persistent and privileged access.
Such access could allow attackers to manipulate system operations, steal sensitive data, disrupt services, or use the compromised system as a foothold for further attacks.
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
I don't know
How can this vulnerability be detected on my network or system? Can you suggest some commands?
[{'type': 'paragraph', 'content': 'This vulnerability can be detected by attempting to access the /api/runscript endpoint while spoofing the HTTP Referer header to include "/fuxa". Successful bypass of authentication indicates the presence of the vulnerability.'}, {'type': 'paragraph', 'content': 'A practical detection method involves sending a crafted HTTP request with a spoofed Referer header and a JSON payload to the /api/runscript endpoint and observing if the server executes the code.'}, {'type': 'list_item', 'content': 'Use a Python script with the requests library to send a POST request to http://<target>/api/runscript with the Referer header set to a value containing "/fuxa".'}, {'type': 'list_item', 'content': 'Example command snippet in Python:\n\nimport requests\n\nheaders = {\'Referer\': \'http://localhost/fuxa\'}\npayload = {\'code\': \'console.log("test")\'}\nresponse = requests.post(\'http://<target>/api/runscript\', json=payload, headers=headers)\nprint(response.text)'}, {'type': 'paragraph', 'content': 'If the server executes the code or returns a response indicating execution, the vulnerability is present.'}] [1]
What immediate steps should I take to mitigate this vulnerability?
Immediate mitigation steps include restricting access to the /api/runscript endpoint and disabling or properly validating the Referer header in the authentication middleware.
Since the vulnerability arises from trusting the Referer header to validate internal requests, ensure that the server does not rely on this header for authentication or implement stricter validation.
If possible, upgrade to a fixed version of FUXA that addresses this vulnerability.
As a temporary workaround, consider firewall rules or network segmentation to limit access to the vulnerable endpoints only to trusted internal sources.
After any exploit attempt or suspected compromise, restart the server to clear any malicious code execution state and verify the integrity of the user database.