explaingit

yagyeshvyas/vibeguard

Analysis updated 2026-05-18

3JavaScriptAudience · developerComplexity · 2/5LicenseSetup · easy

TLDR

A local, offline security scanner and AI agent firewall that finds leaked secrets, injection bugs, and unsafe AI agent behavior in code.

Mindmap

mindmap
  root((VibeGuard))
    What it does
      Scans for leaked secrets
      Finds SQL and XSS injection
      Audits MCP servers
      Blocks unsafe agent actions
    Tech stack
      JavaScript
      npm CLI
      MCP protocol
    Use cases
      Scan AI generated apps
      Guard agent tool calls
      CI security checks
    Audience
      Vibe coders
      Developers
      Security teams

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Scan an AI-generated codebase for hardcoded API keys and open databases before shipping it.

USE CASE 2

Catch SQL injection and cross site scripting bugs that AI-written code commonly introduces.

USE CASE 3

Audit MCP tool servers an AI agent trusts for suspicious or changed configuration.

USE CASE 4

Block an AI agent from sending secrets or personal data to an outside server in real time.

What is it built with?

JavaScriptNode.jsMCP

How does it compare?

yagyeshvyas/vibeguardabhagsain/bayut-maps-ratingsabhishek-kumar09/who-is-imposter
Stars333
LanguageJavaScriptJavaScriptJavaScript
Last pushed2021-04-12
MaintenanceDormant
Setup difficultyeasymoderateeasy
Complexity2/52/53/5
Audiencedevelopergeneralgeneral

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

Runs via a single npx command with no account or telemetry required.

Free to use, modify, and distribute for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

VibeGuard is a security scanner built specifically for code generated by AI coding tools, since the README argues that AI assistants tend to write working code quickly while skipping the security hardening a human developer would normally add. Running one command scans a project in about five seconds and reports problems like hardcoded API keys, SQL injection, and cross site scripting, each labeled by severity along with a suggested fix, and the tool can also attempt to fix some issues automatically. The scanner looks for over 50 kinds of leaked secret keys, from OpenAI and AWS to Stripe and Slack, and flags cases where a database like Supabase has been left open to the public with no row level security. It also traces how untrusted input actually flows through code, so it can confirm, rather than just guess, when user input reaches a SQL query or gets injected into an AI system prompt, which is a common way prompt injection attacks happen. Other checks look for AI agent loops with no limit on how many times they can run, and for cases where text generated by a language model gets passed straight into a command execution function, which could let an attacker run arbitrary commands through a crafted response. Beyond scanning code, VibeGuard can also audit the configuration of MCP tool servers that an AI agent connects to, checking for suspicious or unpinned installs and configuration that changed since it was last approved. A separate real time firewall feature can inspect an agent's actions, like network requests or shell commands, before they run, and block ones that would send a secret key or personal information to an outside server. Everything runs entirely on the user's own machine, with no telemetry and no account required, and it is distributed under the MIT license, meaning it can be used, modified, and shared freely as long as the copyright notice stays intact. It works alongside tools like Claude Code, Cursor, and several other AI coding assistants through a shared plugin protocol.

Copy-paste prompts

Prompt 1
Explain what VibeGuard's SQL injection check catches and why it's confirmed dataflow, not a guess.
Prompt 2
Show me how to wire VibeGuard into Claude Code as an MCP server.
Prompt 3
Walk me through what vibeguard mcp-audit checks for in my configured MCP servers.
Prompt 4
Help me set up VibeGuard's guard-action firewall to block secrets from leaving my machine.
Prompt 5
Summarize the security issues in this scan report and how to fix each one.

Frequently asked questions

What is vibeguard?

A local, offline security scanner and AI agent firewall that finds leaked secrets, injection bugs, and unsafe AI agent behavior in code.

What language is vibeguard written in?

Mainly JavaScript. The stack also includes JavaScript, Node.js, MCP.

What license does vibeguard use?

Free to use, modify, and distribute for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is vibeguard to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is vibeguard for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.