Show HN: VibeGuard – security linter for AI-generated code

VibeGuard v1.0.0, a security linter built specifically for AI-generated code, has been released on GitHub by developer zeroFhacker. The tool runs 47 AI-pattern rules to detect vulnerabilities commonly produced by AI coding assistants like GitHub Copilot, Cursor, Claude, and ChatGPT, including SQL injection, hardcoded secrets, and command injection. It assigns a letter grade (A–F) and provides plain-English fixes, with features such as CI/CD mode and exit codes, distinguishing it from traditional linters like Bandit and Semgrep.

AI coding assistants — GitHub Copilot, Cursor, Claude, ChatGPT — write code fast. Really fast. Faster than any security review can keep up with. The problem is they also confidently produce the same security mistakes over and over. Not because they are bad tools. Because they were trained on millions of code examples — and millions of those examples had security vulnerabilities in them. The exact mistakes AI coding assistants make repeatedly: - SQL queries built with string concatenation instead of parameterized queries - Secrets and API keys hardcoded directly into source files - User input passed to eval , exec , subprocess.shell=True without validation - JWT tokens verified without checking the algorithm — the alg:none bypass - XML parsers configured to allow external entities — XXE vulnerabilities - Insecure random number generation used for security-sensitive values - Path traversal — user-controlled file paths with no sanitization - CORS configured to accept any origin - Debug mode left enabled in production configuration - Pickle deserialization of untrusted data — remote code execution Traditional linters like Bandit and Semgrep catch some of these. But they use generic rules that were not built around the specific patterns AI tools produce. VibeGuard is different — every rule was written by studying actual AI-generated code and cataloguing the exact vulnerability patterns these tools produce. bash $ vibeguard scan --path ./my-ai-generated-project VibeGuard v1.0.0 — AI-Generated Code Security Linter Scanning: ./my-ai-generated-project Running 47 AI-pattern rules... app/database.py:34 CRITICAL SQL INJECTION f-string used in SQL query — classic Copilot pattern app/auth.py:12 CRITICAL HARDCODED SECRET API key assigned to variable — detected by entropy app/utils.py:89 HIGH COMMAND INJECTION subprocess called with shell=True + user input app/api.py:156 HIGH JWT ALG NONE JWT decoded without algorithm verification config/settings.py:8 HIGH DEBUG PRODUCTION DEBUG=True in production settings file app/files.py:44 MEDIUM PATH TRAVERSAL User input used in file path without sanitization app/xml parser.py:23 MEDIUM XXE INJECTION XML parser allows external entities Grade: D 7 findings — 2 critical, 3 high, 2 medium Report saved to vibeguard-report.json Fix these first: app/database.py:34 → Use cursor.execute query, params instead of f-strings app/auth.py:12 → Move to environment variable: os.environ.get 'API KEY' | Feature | VibeGuard | Bandit | Semgrep | |---|---|---|---| | Rules built from AI code patterns | ✅ | ❌ | ❌ | | Letter grade A–F | ✅ | ❌ | ❌ | | Plain English fix for every finding | ✅ | Partial | Partial | | Detects AI-specific anti-patterns | ✅ | ❌ | ❌ | | Zero configuration to start | ✅ | ✅ | ❌ | | CI/CD mode with exit codes | ✅ | ✅ | ✅ | | VS Code extension | Roadmap | ❌ | ✅ | Developers using Copilot, Cursor, Claude, or ChatGPT to write code Security engineers reviewing AI-generated pull requests Engineering teams who have adopted AI coding tools and want automated security checks DevSecOps teams who want AI-specific security gates in their CI/CD pipeline Students learning about the security implications of AI-generated code python3 --version You need version 3.10 or higher. git --version Clone the repo git clone https://github.com/zeroFhacker/vibeguard.git cd vibeguard Create virtual environment python3 -m venv venv source venv/bin/activate Windows: venv\Scripts\activate Install pip install -r requirements.txt PYTHONPATH=. python -m vibeguard.cli scan --path ./my-project PYTHONPATH=. python -m vibeguard.cli scan --path ./app/database.py PYTHONPATH=. python -m vibeguard.cli scan --path . --ci --fail-on high PYTHONPATH=. python -m vibeguard.cli scan --path . --severity critical PYTHONPATH=. python -m vibeguard.cli scan --path . --output report.json PYTHONPATH=. python -m vibeguard.cli rules list - SQL injection via f-string or concatenation - Command injection via shell=True - LDAP injection - XPath injection - Template injection - API keys assigned to variables - Hardcoded passwords in source - AWS/GCP/Azure credentials in code - Private keys in source files - Database connection strings with credentials - JWT decoded without algorithm verification - JWT secret hardcoded - Weak session secret - Missing authentication on sensitive endpoints - Insecure password hashing MD5, SHA1 - Path traversal via user-controlled file paths - XML external entity injection - Eval/exec with user input - Pickle deserialization of untrusted data - YAML load instead of safe load - Debug mode enabled in production - CORS wildcard origin - Insecure cookie settings no HttpOnly, no Secure - Weak TLS configuration - Default admin credentials - MD5 used for security-sensitive hashing - SHA1 used for security-sensitive hashing - Weak random random module for security values - ECB mode encryption - Hardcoded encryption key Add to .github/workflows/security.yml : name: VibeGuard Security Scan on: push, pull request jobs: vibeguard: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: actions/setup-python@v4 with: python-version: '3.11' - run: pip install -r requirements.txt - name: Run VibeGuard run: | PYTHONPATH=. python -m vibeguard.cli scan \ --path . \ --ci \ --fail-on high \ --output vibeguard-report.json - name: Upload report uses: actions/upload-artifact@v4 with: name: vibeguard-security-report path: vibeguard-report.json | Grade | Score | What It Means | |---|---|---| | A | 90–100 | Excellent — no high or critical findings | | B | 75–89 | Good — minor issues only | | C | 60–74 | Needs attention — several medium findings | | D | 40–59 | Poor — high severity findings present | | F | 0–39 | Critical — immediate action required | New AI-pattern rules are always welcome. To add a rule: - Add a RulePattern to vibeguard/rules/patterns.py - Write the regex or AST check - Include: name, description, severity, AI tool that commonly produces this, plain English fix - Add a test in tests/test rules.py See CONTRIBUTING.md for full guidance. MIT — see LICENSE /zeroFhacker/vibeguard/blob/main/LICENSE Part of the open-source security toolkit at github.com/zeroFhacker https://github.com/zeroFhacker