CVE-2026-75130: Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions

Context7 versions up to 2.1.2 have a prompt injection vulnerability (a flaw where attackers can hide malicious commands in input data) in its Custom AI Instructions feature that runs through an MCP server (a protocol for connecting AI tools together). Attackers can use this to steal credentials stored in environment files or delete files on a victim's computer when the AI agent requests routine documentation.