https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Sun, 18 Oct 2026 07:42:24 +0000 https://cve.radiocsirt.org/vuln/bdu:2026-07188 bdu:2026-07188 https://cve.radiocsirt.org/vuln/bdu:2026-07188 https://cve.radiocsirt.org/vuln/euvd-2026-319096 EUVD-2026-319096 https://cve.radiocsirt.org/vuln/euvd-2026-319096 https://cve.radiocsirt.org/vuln/fkie_cve-2026-45350 <p>Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. This vulnerability is fixed in 0.8.6.</p> <p>Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.8.6, there is a vulnerability in chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access. In the chat_completion API, the parameters tool_ids and tool_servers are supplied by the user. These parameters are used to create a tools_dict by the middleware. This is then used by get_tool_by_id to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. This vulnerability is fixed in 0.8.6.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2026-45350 https://cve.radiocsirt.org/vuln/ghsa-4pcg-253r-rf9w <p><strong>Affected:</strong> PyPI: open-webui</p> <p>### Summary Open WebUI v0.6.43 contains a vulnerability in its chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access.</p> <p>### Details In the [chat_completion](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1529) API, the parameters [tool_ids and tool_servers](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1613-L1614) are supplied by the user. These parameters are used to [create a tools_dict by the middleware](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/utils/middleware.py#L1394). This is then used by [get_tool_by_id](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/models/tools.py#L139) to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. ### PoC To reproduce the issue, create an admin user and create an external tool via the admin settings. Set the type to &#34;MCP Streamable HTTP&#34; for the tool, a…</p> <p><strong>Affected:</strong> PyPI: open-webui</p> <p>### Summary Open WebUI v0.6.43 contains a vulnerability in its chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access.</p> <p>### Details In the [chat_completion](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1529) API, the parameters [tool_ids and tool_servers](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1613-L1614) are supplied by the user. These parameters are used to [create a tools_dict by the middleware](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/utils/middleware.py#L1394). This is then used by [get_tool_by_id](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/models/tools.py#L139) to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. ### PoC To reproduce the issue, create an admin user and create an external tool via the admin settings. Set the type to &#34;MCP Streamable HTTP&#34; for the tool, a…</p> https://cve.radiocsirt.org/vuln/ghsa-4pcg-253r-rf9w https://cve.radiocsirt.org/vuln/pysec-2026-2700 <p><strong>Affected:</strong> PyPI: open-webui</p> <p>### Summary Open WebUI v0.6.43 contains a vulnerability in its chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access.</p> <p>### Details In the [chat_completion](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1529) API, the parameters [tool_ids and tool_servers](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1613-L1614) are supplied by the user. These parameters are used to [create a tools_dict by the middleware](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/utils/middleware.py#L1394). This is then used by [get_tool_by_id](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/models/tools.py#L139) to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. ### PoC To reproduce the issue, create an admin user and create an external tool via the admin settings. Set the type to &#34;MCP Streamable HTTP&#34; for the tool, a…</p> <p><strong>Affected:</strong> PyPI: open-webui</p> <p>### Summary Open WebUI v0.6.43 contains a vulnerability in its chat completion API, which allows attackers to bypass tool restrictions, potentially enabling unauthorized actions or access.</p> <p>### Details In the [chat_completion](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1529) API, the parameters [tool_ids and tool_servers](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/main.py#L1613-L1614) are supplied by the user. These parameters are used to [create a tools_dict by the middleware](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/utils/middleware.py#L1394). This is then used by [get_tool_by_id](https://github.com/open-webui/open-webui/blob/a7271532f8a38da46785afcaa7e65f9a45e7d753/backend/open_webui/models/tools.py#L139) to retrieve the appropriate tool. However, there is no checks in that ensures the user that uses the API has permission to use the tool, meaning that a user can invoke any server tool by supplying the correct tool_id or tool_servers parameters via the chat completion API. Moreover, the authentication token stored in the server would be used when invoking the tool, so the tool will be invoked with the server privilege. ### PoC To reproduce the issue, create an admin user and create an external tool via the admin settings. Set the type to &#34;MCP Streamable HTTP&#34; for the tool, a…</p> https://cve.radiocsirt.org/vuln/pysec-2026-2700