Browse / System Prompt Leakage / CVE-2026-45387
Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)
- Class
- System Prompt Leakage (filed by a model that read the advisory)
- Technique
- Information exposure
- Affected
- open-webui (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
- EPSS
- 0.2% chance of exploitation in 30 days
How it works, in short
Users granted read access to a shared model can fetch its details by ID through a model endpoint that returns the hidden system prompt. (Our summary, written by a model. The source text is below.)
Details
Summary
When setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model's system prompt.
However users may consider their system prompt confidential, so we consider this a security issue.
Compare https://genai.owasp.org/llmrisk/llm072025-system-prompt-leakage/ or prompt injections to get popular chatbots on the internet to reveal their prompt.
Details
We discovered that users can open the workspace model edit page /workspace/models/edit?id=notmymodel for models that do not appear in their workspace.
Saving is not possible, that permission check is correct.
On the API level: