Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded passwords, or code security checks.
.claude/skills/zebbern-code-vuln-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 22% | 0% |
A code security scanning tool with three core scanning capabilities:
bash# Scan the current directory (all checks) python3 scripts/security_scan.py . # Scan dependencies only python3 scripts/security_scan.py --mode deps . # Detect secret leaks only python3 scripts/security_scan.py --mode secrets /path/to/project # Detect OWASP security patterns only python3 scripts/security_scan.py --mode owasp . # Output report in JSON format python3 scripts/security_scan.py --format json --output report.json . # Only show findings at high severity and above python3 scripts/security_scan.py --severity high .
Automatically detects the project type and invokes the appropriate tool:
| Project Type | Detection File | Tool Used | |---|---|---| | Node.js | package.json + package-lock.json | npm audit | | Python | requirements.txt / pyproject.toml / Pipfile | pip-audit |
If the corresponding audit tool is not installed, a helpful message is displayed instead of an error.
Detection is performed in two ways:
Regex Matching: Covers common secret formats
| Secret Type | Example Pattern | |---|---| | AWS Access Key | 20-character string starting with AKIA | | GitHub Token | Starts with ghp_ or github_pat_ | | Slack Token | Starts with xoxb- or xoxp- | | Stripe Key | Starts with sk_live_ or pk_live_ | | Private Key File | -----BEGIN PRIVATE KEY----- | | Generic API Key | Format like api_key = "..." | | Credentials in URL | https://user:pass@host | | JWT Token | eyJ... format |
Shannon Entropy Analysis: Computes information entropy for string constants in code (threshold > 4.5 and length >= 20) to discover secrets in non-standard formats.
Covers statically detectable security patterns from the OWASP Top 10:
| OWASP Category | Detection Patterns | |---|---| | A02: Cryptographic Failures | Weak hashes (MD5/SHA1), weak ciphers (DES/RC4) | | A03: Injection | SQL injection, command injection (os.system / subprocess shell / eval / exec), XSS (innerHTML / document.write / dangerouslySetInnerHTML / v-html) | | A04: Insecure Design | Path traversal | | A05: Security Misconfiguration | Debug mode enabled, CORS wildcard, binding to 0.0.0.0 | | A08: Integrity Failures | Insecure deserialization (pickle / yaml.load / marshal / unserialize) | | A10: SSRF | User input passed directly to HTTP requests |
Supported languages: Python, JavaScript/TypeScript, Java, PHP, Ruby, Go, and more.
| Parameter | Description | Default | |---|---|---| | TARGET | Directory to scan | Current directory | | --mode MODE | Scan mode: all, deps, secrets, owasp | all | | --format FORMAT | Output format: text, json | text | | --output FILE | Output file path | stdout | | --severity LEVEL | Minimum reporting level: low, medium, high, critical | low | | --exclude-dir DIR | Additional directories to exclude (repeatable) | - | | --max-file-kb SIZE | Maximum file size to scan in KB | 512 | | -h, --help | Show help | - |
=== Security Scan Report ===
Target: /path/to/project
Modules: deps, secrets, owasp
[CRITICAL] AWS Access Key ID
File: src/config.py:15
Code: AWS_KEY = "AKIAIOSFODNN7EXAMPLE"
[HIGH] SQL Injection (f-string)
File: src/db.py:42
Code: cursor.execute(f"SELECT * FROM users WHERE id={user_id}")
--- Summary ---
Critical: 1 | High: 1 | Medium: 0 | Low: 0
Total findings: 2json{ "target": "/path/to/project", "scan_time": "2026-04-14T10:30:00", "findings": [ { "scanner": "secrets", "name": "AWS Access Key ID", "severity": "critical", "file": "src/config.py", "line": 15, "snippet": "AWS_KEY = \"AKIAIOSFODNN7EXAMPLE\"", "category": "secret-pattern" } ], "summary": {"critical": 1, "high": 0, "medium": 0, "low": 0, "total": 1} }
| Exit Code | Meaning | |---|---| | 0 | No findings | | 1 | Findings present (at least one security issue) | | 2 | Scanner internal error |
npm (for Node.js projects), pip-audit (for Python projects)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 8,244 | 13,215 | +60% | 1 | 1 | 0% | 962 | 2,682 | +179% | 0 | 0 | — |
case-02 | fail→pass | 5,451 | 1,433 | -74% | 1 | 1 | 0% | 1,050 | 1,634 | +56% | 0 | 0 | — |
case-03 | fail→fail | 6,349 | 6,965 | +10% | 1 | 1 | 0% | 751 | 2,392 | +219% | 0 | 0 | — |
case-04 | pass→pass | 7,087 | 2,003 | -72% | 1 | 1 | 0% | 1,450 | 1,774 | +22% | 0 | 0 | — |
case-05 | pass→pass | 13,626 | 2,532 | -81% | 1 | 1 | 0% | 2,581 | 1,790 | -31% | 0 | 0 | — |
case-06 | fail→pass | 12,938 | 3,091 | -76% | 1 | 1 | 0% | 2,341 | 1,944 | -17% | 0 | 0 | — |
case-07 | fail→pass | 20,786 | 2,571 | -88% | 1 | 1 | 0% | 2,090 | 1,829 | -12% | 0 | 0 | — |
case-08 | pass→pass | 15,056 | 2,228 | -85% | 1 | 1 | 0% | 2,842 | 1,813 | -36% | 0 | 0 | — |
case-09 | pass→pass | 13,999 | 3,261 | -77% | 1 | 1 | 0% | 2,776 | 1,873 | -33% | 0 | 0 | — |
case-10 | pass→pass | 13,328 | 5,320 | -60% | 1 | 1 | 0% | 2,488 | 2,484 | -0% | 0 | 0 | — |
case-11 | pass→pass | 15,311 | 10,315 | -33% | 1 | 1 | 0% | 2,956 | 3,467 | +17% | 0 | 0 | — |
case-12 | pass→pass | 8,299 | 3,027 | -64% | 1 | 1 | 0% | 1,482 | 1,710 | +15% | 0 | 0 | — |
case-13 | pass→pass | 6,009 | 3,362 | -44% | 1 | 1 | 0% | 994 | 1,661 | +67% | 0 | 0 | — |
case-14 | fail→pass | 8,558 | 3,614 | -58% | 1 | 1 | 0% | 1,442 | 1,677 | +16% | 0 | 0 | — |
case-15 | fail→pass | 7,499 | 3,007 | -60% | 1 | 1 | 0% | 1,366 | 1,662 | +22% | 0 | 0 | — |
case-16 | pass→pass | 4,629 | 2,801 | -39% | 1 | 1 | 0% | 715 | 1,661 | +132% | 0 | 0 | — |
case-17 | pass→pass | 3,045 | 2,054 | -33% | 1 | 1 | 0% | 495 | 1,588 | +221% | 0 | 0 | — |
case-18 | fail→pass | 6,342 | 2,535 | -60% | 1 | 1 | 0% | 1,187 | 1,694 | +43% | 0 | 0 | — |
case-19 | fail→pass | 9,707 | 2,809 | -71% | 1 | 1 | 0% | 2,061 | 1,982 | -4% | 0 | 0 | — |
case-20 | pass→pass | 4,332 | 3,420 | -21% | 1 | 1 | 0% | 841 | 2,132 | +154% | 0 | 0 | — |
case-21 | pass→pass | 6,593 | 4,602 | -30% | 1 | 1 | 0% | 1,329 | 2,266 | +71% | 0 | 0 | — |
case-22 | pass→pass | 9,251 | 4,681 | -49% | 1 | 1 | 0% | 1,997 | 2,383 | +19% | 0 | 0 | — |
case-23 | pass→pass | 15,647 | 2,825 | -82% | 1 | 1 | 0% | 3,312 | 1,844 | -44% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +30 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.