
vibelint
Catch insecure AI code before it ships
An agent can write and edit files for you, one bad suggestion can ship a hardcoded secret, missing auth check, unsafe query, or exposed env variable before you even notice.
VibeLint is an open-source security layer for AI coding workflows. It connects through MCP and scans AI-generated code before it gets written, flagging risky patterns in real time.
The goal is simple: keep the speed of vibe coding, but add a safety net before mistakes reach production.
Would love feedback from other founders and devs building with AI agents.
About
vibelint started as a personal problem i needed to fix , as a developer a started using AI to write most of my code as anyone else, ai wrote good functioning code but not secure so i built a security layer to protect it

Comment