Scans every push automatically

Security Scanner for
Vibe-Coded Apps

Install the GitHub App. Push code. Get security findings as PR annotations. One click, zero config — built for developers who build with AI.

Install GitHub App — Free Dashboard
No code stored. Scan results only. Learn more

The Vibe Coding Security Crisis

0–62%
of AI-generated code contains security vulnerabilities
Stanford HAI Study, 2025
0
new CVEs traced directly to AI-generated code in March 2026 alone
NVD Database, March 2026
0%
of all code on GitHub is now AI-generated — most unscanned
GitHub Octoverse Report, 2025

Two-Layer Defense

Everything you need to secure AI code

Static analysis catches what's in the code. Behavioral probing catches what the model does at runtime. Most tools only do one.

🔍

Layer 1 — Static Analysis

36 Semgrep rules covering AI-specific and traditional vulnerabilities. Catches prompt injection, hardcoded secrets, SQL injection, command injection, XSS, prototype pollution, insecure JWT, CORS misconfig, and more — across Python and JavaScript.

36 Rules Semgrep Engine Zero False Positives Python + JS/TS
🏆 OWASP LLM Top 10 Coverage
🤖

Layer 2 — Behavioral Probing

15 behavioral probes test your live LLM endpoints. Detects scope violations, prompt injection at runtime, data extraction attempts, and persona abandonment vulnerabilities.

15 Probes Live Endpoint SCOPE / INJECTION / EXTRACTION
⚙️

GitHub App — Zero Config

Install in one click, pick your repos. Every push and PR is auto-scanned. Findings appear as Check Run annotations directly in your PRs — no CI setup, no config files, no pipeline changes.

One-Click Install Auto-Scan on Push PR Annotations
📊

Rich Reporting

Findings appear as Check Run annotations directly on your PRs — inline with your code. Track trends over time in the dashboard with severity breakdowns and remediation guidance.

PR Annotations Dashboard Severity Breakdown Fix Guidance
🚀 One-click GitHub App install
🔒 Never stores code or secrets
⚡ Scans in under 60 seconds
📊 Dashboard with scan history

Get Running in Minutes

How it works

Three steps from install to your first security report.

1

Install

Click "Install GitHub App", pick the repos you want scanned. Takes 30 seconds — no config files, no CI changes.

2

Push Code

Every push and PR is automatically scanned with all 36 rules. Results appear as Check Run annotations directly on your commits.

3

Fix

Each finding shows the exact file, line, vulnerability type, and how to fix it. Track everything in your dashboard.

GitHub Check Run — vibecodescanner
❌ vibecodescanner — FAIL
5 findings in 4 files | 2 CRITICAL | 2 HIGH | 1 MEDIUM
─── Annotations ────────────────────────────────────
⚠ auth/client.py:12 — Hardcoded OpenAI API key in source code
Fix: Move to environment variable, use os.getenv("OPENAI_API_KEY")
 
⚠ db/queries.py:47 — Unsanitized LLM output in SQL query
Fix: Use parameterized queries, never interpolate LLM output
 
⚠ api/chat.py:23 — User input concatenated into prompt
Fix: Use template with input validation and sanitization
 
⚠ tools/mcp.py:8 — MCP tool has unrestricted filesystem access
Fix: Restrict to specific directories with allowlist
 
──────────────────────────────────────────────────
🔎 View full results in the Dashboard →

Competitive Landscape

Why not just use Garak or Promptfoo?

Existing tools only solve half the problem. vibecodescanner is the only tool that does both layers with zero config.

Tool Static Analysis Behavioral Probing OWASP LLM Coverage Auto-Scan Free Tier Status
>_ vibecodescanner ✓ 36 rules ✓ 15 probes ✓ Full ✓ Every push ✓ Free Active
Garak ✗ ✓ Partial ✗ ✓ Active
Promptfoo ✗ ✓ Partial ✗ Freemium Acquired by OpenAI
Manual Review Slow Incomplete ✗ ✗ Human hours Unscalable
Bandit / Semgrep ✓ ✗ ✗ ✗ ✓ Active

Privacy-First

Your Code Never Leaves GitHub

Zero code storage

Scans run through the GitHub API using the permissions you grant. We only store finding metadata — file name, line number, severity, and fix. Never your actual code, secrets, or PII.

🔒 Install GitHub App

Simple Pricing

Start free, scale when ready

Start scanning for free. Pro and Enterprise add private repos, unlimited scans, and team features.

Free
$0 / forever
GitHub App for public repos. Auto-scan every push with all 36 rules.
  • ✓ 36 security rules (AI + traditional)
  • ✓ Public repos (up to 5)
  • ✓ 5 scans per month
  • ✓ Auto-scan on push
  • ✓ PR annotations with fix guidance
  • ✓ Dashboard with scan history
  • ✓ No credit card required
Install GitHub App
MOST POPULAR
Pro
$49 / month
Everything in Free plus a hosted dashboard, CI/CD integration, team management, and scan history.
  • ✓ Everything in Free
  • ✓ Private repos + unlimited repos
  • ✓ Unlimited scans
  • ✓ Web dashboard + scan history (90 days)
  • ✓ Team management (5 seats)
  • ✓ Slack + email alerts
  • ✓ Priority support
Start Free Trial
Enterprise
Custom
For security teams and organizations that need SSO, dedicated support, and custom rule development.
  • ✓ Everything in Pro
  • ✓ SSO / SAML
  • ✓ Unlimited seats
  • ✓ Custom rules development
  • ✓ On-premise CLI COMING SOON
  • ✓ Dedicated Slack channel
  • ✓ SLA guarantees
Contact Sales

Questions

Frequently Asked Questions

No. When you push code, GitHub sends us a webhook. We use the GitHub API (with the read-only permissions you granted) to scan the repo, then immediately discard it. We only store finding metadata: file name, line number, severity, vulnerability type, and a remediation suggestion. We never store your actual code, API keys, secrets, or any PII.
Three permissions, all minimal:

Contents: Read-only — to read your code for scanning. We never write to your repo.
Checks: Read & write — to post scan results as Check Run annotations on your commits and PRs.
Pull Requests: Read-only — to know which PR triggered the scan.

That's it. No write access to your code. No access to issues, wikis, settings, or anything else.
36 Semgrep rules across two categories:

AI/LLM Security (22 rules): Prompt injection, hardcoded API keys, LLM output in SQL, dangerous tool execution, overprivileged MCP, unsafe pickle/torch deserialization, LLM output in auth decisions, credential forwarding to prompts, LangChain injection, dangerouslySetInnerHTML XSS, LLM-driven SSRF & path traversal, dangerous --yolo/--skip-permissions flags

Traditional Security (14 rules): SQL injection (f-strings/concat), command injection, insecure YAML load, Flask debug mode, weak password hashing (MD5/SHA1), open redirect, JWT without verification, JS command injection, NoSQL injection, reflected XSS, prototype pollution, insecure postMessage, insecure cookies, CORS wildcard

Every finding includes a specific remediation — not just "fix this" but exactly how.
Snyk and Dependabot scan your dependencies for known CVEs. We scan your actual code for AI-specific vulnerability patterns — things like prompt injection, LLM output being used in SQL, or API keys that Copilot pasted into your source. These tools are complementary. Use Dependabot for supply chain, use us for the code AI wrote for you.
No. Scans run asynchronously — your push or PR goes through immediately. The Check Run result appears within 30–60 seconds. It never blocks your merge or deploy unless you configure branch protection rules to require it.
Free tier includes 5 scans per month on public repos. When you hit the limit, the Check Run will show a neutral status with a message to upgrade. Your code still pushes fine — scanning just pauses until next month or you upgrade to Pro ($49/month) for unlimited scans and private repo support.
An on-premise CLI is coming soon as part of the Enterprise plan. It will run entirely on your infrastructure — no data leaves your network. Contact us if you're interested in early access.
One click. Go to GitHub Settings → Applications → vibecodescanner → Uninstall. All permissions are revoked instantly. We delete your installation record from our database. No lock-in, no cancellation flow.