OpenCode Flaw Enables Code Execution via Malicious MCP Servers

A critical vulnerability rated 9.8/10 in OpenCode's MCP sign-in flow allows malicious MCP servers to execute code on users' machines, according to a disclosure that was privately reported on August 29 and made public on October 19. A fix shipped in OpenCode version 1.18.33 on September 28. The flaw matters because MCP servers are widely used to connect AI coding agents to external tools, so a malicious server can turn a routine sign-in into arbitrary code execution.

A critical flaw in OpenCode's MCP sign-in flow, rated 9.8/10 in severity, allows malicious MCP servers to execute code, posing a significant threat to users. This vulnerability was privately reported on August 29 and publicly disclosed on October 19, with a fix released in version 1.18.33 on September 28.