MMMarhoon@marhoons·2d99c15c7Bitdefender found 22 malicious GitHub links targeting AI coding agents Some abuse agent instructions, hooks and MCP configs to execute hidden code 🔥A reminder that cloning random repos and trusting every instruction is risky1Quote
SBSuliman Benhalim@sulimanbenhalim·2d1785fedthe trust prompt on a fresh clone is the one dialog worth actually reading 😅 #claudecode11:41 · Nov 18, 2026 · commit 1785fedQuoteReply