Snitch Docs

Quick start

Run your first Snitch security scan in under a minute.

The fastest path: install the Plugin into the AI coding tool you already use, ask your AI to run a security audit, read the findings.

1. Pick your tool

You want to...Use this
Audit a codebase from inside your AI editorPlugin
Run scans from any terminal on your deviceCLI
Scan every pull request automaticallyGitHub Action

2. Install

Plugin

Buy the Plugin once, get a one-line install command tied to your account. Drop it into Claude Code, Cursor, Codex, Windsurf, or any of the 30+ supported AI tools. The skill loads the 72-category methodology and sits ready.

CLI

Subscribe and download the binary from your dashboard. Run snitch scan in any repo. The CLI shells out to your locally-installed Claude / Codex / Gemini, or uses an OpenRouter key you supply.

snitch scan

GitHub Action

Subscribe, paste a workflow YAML into .github/workflows/snitch.yml, push. The Action runs on every pull request out of the box.

name: Snitch
on: pull_request
permissions:
  contents: read
  pull-requests: write
  models: read
jobs:
  scan:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: snitchplugin/snitch-github-action@v1
        with:
          snitch-license-key: ${{ secrets.SNITCH_LICENSE_KEY }}

3. Read findings

Each finding has a severity (Critical / High / Medium / Low), a CWE reference, the exact file and line, the risk, and a suggested fix. The CLI and Action also write a SARIF file that uploads cleanly to GitHub Code Scanning.

Next

On this page

Snitch uses AI to generate findings. AI can make mistakes, miss issues, or flag false positives, even with guardrails. Snitch is not responsible for actions taken based on AI output. Read the full AI disclaimer