Описание
Malicious website can execute commands on the local system through XSS in the OpenCode web UI
Summary
A malicious website can abuse the server URL override feature of the OpenCode web UI to achieve cross-site scripting on http://localhost:4096. From there, it is possible to run arbitrary commands on the local system using the /pty/ endpoints provided by the OpenCode API.
Code execution via OpenCode API
- The OpenCode API has
/pty/endpoints that allow spawning arbitrary processes on the local machine. - When you run
opencodein your terminal, OpenCode automatically starts an HTTP server onlocalhost:4096that exposes the API along with a web interface. - JavaScript can make arbitrary same-origin
fetch()requests to the/pty/API endpoints. Therefore, JavaScript execution onhttp://localhost:4096gets you code execution on local the machine.
JavaScript execution on localhost:4096
The markdown renderer used for LLM responses will insert arbitrary HTML into the DOM. There is no sanitization with DOMPurify or even a CSP on the web interface to prevent JavaScript execution via HTML injection.
This means controlling the LLM response for a chat session gets you JavaScript execution on the http://localhost:4096 origin. This alone would not be enough for a 1-click exploit, but there's functionality in packages/app/src/app.tsx to allow specifying a custom server URL in a ?url=... parameter:
Using this custom server URL functionality, you can make the web UI connect to and load chat sessions from an OpenCode instance on another URL. For example, tricking a user into opening http://localhost:4096/Lw/session/ses_45d2d9723ffeHN2DLrTYMz4mHn?url=https://opencode.attacker.example in their browser would load and display ses_45d2d9723ffeHN2DLrTYMz4mHn from the attacker-controlled server at https://opencode.attacker.example.
Note on exploitability
Because the localhost web UI proxies static resources from a remote location, the OpenCode team was able to prevent exploitation of this issue by making a server-side change to no longer respect the ?url= parameter. This means the specific vulnerability used to achieve XSS on the localhost web UI no longer works as of Fri, 09 Jan 2026 21:36:31 GMT. Users are still strongly encouraged to upgrade to version 1.1.10 or later, as this disables the web UI/OpenCode API to reduce the attack surface of the application. Any future XSS vulnerabilities in the web UI would still impact users on OpenCode versions before 1.10.0.
Proof of Concept
A simple way to serve a malicious chat session is by setting up mitmproxy in front of a real OpenCode instance. This is necessary because the OpenCode web UI must load a bunch of resources before it loads and displays the chat session.
- Spawn an OpenCode instance in a Docker container
- Create a file called
plugin.pywith the contents below
- Start mitmproxy with the plugin in reverse proxy mode
- Start OpenCode in your terminal as the victim
-
Visit the following URL in a browser on the same machine running OpenCode: http://localhost:4096/Lw/session/ses_45d2d9723ffeHN2DLrTYMz4mHn?url=http://localhost:12345
-
Confirm the file
albert-was-here.txtwas created in the/tmp/directory
Пакеты
opencode-ai
< 1.1.10
1.1.10
Связанные уязвимости
OpenCode is an open source AI coding agent. The markdown renderer used for LLM responses will insert arbitrary HTML into the DOM. There is no sanitization with DOMPurify or even a CSP on the web interface to prevent JavaScript execution via HTML injection. This means controlling the LLM response for a chat session gets JavaScript execution on the http://localhost:4096 origin. This vulnerability is fixed in 1.1.10.