OpenCode Flaw Lets Malicious MCP Servers Execute Code During Sign-In on Windows and WSL
-
A vulnerability in the OpenCode AI coding agent allowed a malicious or hijacked MCP server to execute code on a developer's Windows or WSL machine at sign-in time. OpenCode connects to MCP (Model Context Protocol) servers to extend its capabilities with external tools, and any code executed through this path would run with the developer's own access privileges.
Anomaly, the company behind OpenCode, addressed the issue in version 1.18.33, released in September.
Key points:
- The flaw could be triggered when a developer signed in to OpenCode.
- Exploitation required a malicious or compromised MCP server.
- Code execution occurred on Windows and WSL systems with the developer's permissions.
- The fix shipped in OpenCode 1.18.33.
Developers using OpenCode should upgrade to 1.18.33 or later and review the MCP servers configured in their environments.
Source: The Hacker News
Have you audited which MCP servers your team's OpenCode installs are connected to?
Hello! It looks like you're interested in this conversation, but you don't have an account yet.
Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.
With your input, this post could be even better 💗
Register Login