GHSA-JH9G-8JQW-M2QX

Vulnerability from github – Published: 2026-05-14 20:25 – Updated: 2026-05-19 15:59
VLAI?
Summary
Open WebUI Exposes System Prompt to Regular User [Non-Admin]
Details

Summary

A regular user [non-admin] can view the system prompt of the model which is set by an admin.

Details

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

Affected System

Open WebUI v0.6.40 "main" branch

Vulnerability Details and Advisory from OWASP

LLM07:2025 System Prompt Leakage - https://genai.owasp.org/llmrisk/llm072025-system-prompt-leakage/

PoC

1. Regular User [Non-Admin] login on Open WebUI application. 2. A series of web requests get generated by the application, and the http://IP:8080/api/models? is also gets generated by application . 3. The response of http://IP:8080/api/models? web request reveals the system prompt of all the available models which is set is by the admin on models pages in workspace. system prompt leak

Web Request

GET /api/models? HTTP/1.1 Host: localhost:8080 sec-ch-ua-platform: "Linux" authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjdmYjUxMmFhLTBmMTAtNDRkZi1iOWY1LThmNDg2MWFhNWFmOCIsImV4cCI6MTc2NjU2MjE5OH0.yJpavBynKItPQv76SMGKK012JIf29PVUv9sjuCDuRGQ Accept-Language: en-US,en;q=0.9 sec-ch-ua: "Chromium";v="141", "Not?A_Brand";v="8" sec-ch-ua-mobile: ?0 User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/141.0.0.0 Safari/537.36 Accept: application/json Content-Type: application/json Sec-Fetch-Site: same-origin Sec-Fetch-Mode: cors Sec-Fetch-Dest: empty Referer: http://localhost:8080/ Accept-Encoding: gzip, deflate, br Cookie: token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjdmYjUxMmFhLTBmMTAtNDRkZi1iOWY1LThmNDg2MWFhNWFmOCIsImV4cCI6MTc2NjU2MjE5OH0.yJpavBynKItPQv76SMGKK012JIf29PVUv9sjuCDuRGQ Connection: keep-alive

Impact

1. System prompts can reveal the model instructions, providing an attackers with inside knowledge about the system capabilities and bypass restrictions. 2. Attacker can perform content manipulation affecting the input/output of the model.

Details from MITRE ATLAS

Discover LLM System Information - https://atlas.mitre.org/techniques/AML.T0069 Discover LLM System Information: System Instruction Keywords - https://atlas.mitre.org/techniques/AML.T0069.001 Discover LLM System Information: System Prompt - https://atlas.mitre.org/techniques/AML.T0069.002

Recommendation

1. The web response should not reveal system prompt and related internal/back-end details regarding the model to the regular user. 2. Only the model name and non-sensitive details should be revealed to regular user and internal/back-end details should not be disclosed.

Show details on source website

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.8.8"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "open-webui"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.8.9"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-45351"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-200"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-14T20:25:04Z",
    "nvd_published_at": "2026-05-15T22:16:55Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\n_A regular user [non-admin] can view the system prompt of the model which is set by an admin._\n\n### Details\n_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_\n\n### Affected System\n_Open WebUI v0.6.40 \"main\" branch_\n\n### Vulnerability Details and Advisory from OWASP\nLLM07:2025 System Prompt Leakage - https://genai.owasp.org/llmrisk/llm072025-system-prompt-leakage/\n\n\n### PoC\n_1. Regular User [Non-Admin] login on Open WebUI application._\n_2. A series of web requests get generated by the application, and the http://IP:8080/api/models? is also gets generated by application ._\n_3. The response of http://IP:8080/api/models? web request reveals the system prompt of all the available models which is set is by the admin on models pages in workspace._\n\u003cimg width=\"940\" height=\"352\" alt=\"system prompt leak\" src=\"https://github.com/user-attachments/assets/bd2c76f1-398f-4bc8-a8b2-5e14a768c560\" /\u003e\n\n### Web Request\nGET /api/models? HTTP/1.1\nHost: localhost:8080\nsec-ch-ua-platform: \"Linux\"\nauthorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjdmYjUxMmFhLTBmMTAtNDRkZi1iOWY1LThmNDg2MWFhNWFmOCIsImV4cCI6MTc2NjU2MjE5OH0.yJpavBynKItPQv76SMGKK012JIf29PVUv9sjuCDuRGQ\nAccept-Language: en-US,en;q=0.9\nsec-ch-ua: \"Chromium\";v=\"141\", \"Not?A_Brand\";v=\"8\"\nsec-ch-ua-mobile: ?0\nUser-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/141.0.0.0 Safari/537.36\nAccept: application/json\nContent-Type: application/json\nSec-Fetch-Site: same-origin\nSec-Fetch-Mode: cors\nSec-Fetch-Dest: empty\nReferer: http://localhost:8080/\nAccept-Encoding: gzip, deflate, br\nCookie: token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjdmYjUxMmFhLTBmMTAtNDRkZi1iOWY1LThmNDg2MWFhNWFmOCIsImV4cCI6MTc2NjU2MjE5OH0.yJpavBynKItPQv76SMGKK012JIf29PVUv9sjuCDuRGQ\nConnection: keep-alive\n\n\n### Impact\n_1. System prompts can reveal the model instructions, providing an attackers with inside knowledge about the system capabilities and bypass restrictions._\n_2. Attacker can perform content manipulation affecting the input/output of the model._\n\n### Details from MITRE ATLAS\nDiscover LLM System Information - https://atlas.mitre.org/techniques/AML.T0069\nDiscover LLM System Information: System Instruction Keywords - https://atlas.mitre.org/techniques/AML.T0069.001\nDiscover LLM System Information: System Prompt - https://atlas.mitre.org/techniques/AML.T0069.002\n\n\n### Recommendation\n_1. The web response should not reveal system prompt and related internal/back-end details regarding the model to the regular user._\n_2. Only the model name and non-sensitive details should be revealed to regular user and internal/back-end details should not be disclosed._",
  "id": "GHSA-jh9g-8jqw-m2qx",
  "modified": "2026-05-19T15:59:58Z",
  "published": "2026-05-14T20:25:04Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-jh9g-8jqw-m2qx"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45351"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/open-webui/open-webui"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/releases/tag/v0.8.9"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Open WebUI Exposes System Prompt to Regular User [Non-Admin]"
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Loading…

Detection rules are retrieved from Rulezet.

Loading…

Loading…