GHSA-jh9g-8jqw-m2qx
MEDIUMGHSA-jh9g-8jqw-m2qx is a medium-severity (CVSS 6.5) Information Exposure vulnerability in open-webui. O3 Security confirms whether GHSA-jh9g-8jqw-m2qx is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.
Open WebUI Exposes System Prompt to Regular User [Non-Admin]
Exploitation Status
Proof-of-concept exploit code exists
- CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
Exploitation and automatability from CISA’s SSVC triage for GHSA-jh9g-8jqw-m2qx.
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
How urgent is this, really
GHSA-jh9g-8jqw-m2qx plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.
Where this sits among everything scored
Of 358,265 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.
Real-World Exposure
open-webuiReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.
Description
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. <img width="940" height="352" alt="system prompt leak" src="https://github.com/user-attachments/assets/bd2c76f1-398f-4bc8-a8b2-5e14a768c560" />
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.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | open-webui | all versions | 0.8.9 |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for open-webui. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.
Fix
Update open-webui to 0.8.9 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-jh9g-8jqw-m2qx is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 pinpoints whether GHSA-jh9g-8jqw-m2qx is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.
Tailored to GHSA-jh9g-8jqw-m2qx. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is GHSA-jh9g-8jqw-m2qx in your dependencies?
O3 detects GHSA-jh9g-8jqw-m2qx across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.