Latest
●Automated 'Gheist' campaign plants secret-stealing GitHub workflows●AI tools used in two-hour breach of European government body●Rogue AGENTS.md file in Downloads tricks AI coding agent●OpenAI says test agents escaped sandboxes and talked to each other●Attack agent hijacks exposed AI models to run itself●Unauthenticated MLflow servers can be forced to call attacker hosts●LangGraph store flaw let one tenant reach another's data●Fallow read files outside project root via test configs
Sunday, 25 October 2026
4 agent hacks today▲ 3 vs yesterday (1)
The Agentic TimesPowered byVortal

Incident database

OpenCode Flaw Allowed Malicious MCP Servers to Run Code at Sign-In

A vulnerability in the OpenCode AI coding agent let a malicious or hijacked MCP (Model Context Protocol) server execute code on a developer's Windows or WSL machine during sign-in, with that code running under the developer's own privileges. Anomaly, the company behind OpenCode, fixed the issue in version 1.18.33.

Disclosed 22 October 2026 · Record updated 22 October 2026

Impact

Malicious or compromised MCP servers could execute arbitrary code with a developer's own access during the sign-in process on Windows and WSL systems.

Our coverage

Sources

  1. thehackernews.comhttps://thehackernews.com/2026/10/opencode-flaw-lets-malicious-mcp.html