About security-audit
security-audit is a security auditing skill for developers reviewing applications, cloud infrastructure, and GitHub repositories. It combines reference guidance with scripts that detect a project stack and run matching scanners, alongside focused PHP/TYPO3 checks.
Key features
- 01OWASP, CWE, and CVSS audit guidance
- 02Application and API vulnerability checks
- 03Cloud and IaC security references
- 04AI agent configuration audits
- 05Stack-detecting audit dispatcher
- 06PHP and GitHub audit scripts
Use cases
- 01Reviewing an application for common vulnerabilities
- 02Checking AWS or IaC security configurations
- 03Auditing AI agent files and hooks
- 04Running security checks on a GitHub repository
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ netresearch/ security-audit-skill --skill security-auditAfter installing, type/security-auditin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
checkpoints.yamlevals/evals.jsonreferences/api-key-encryption.mdapi-security.mdauthentication-patterns.mdautomated-scanning.mdaws-security.mdci-security-pipeline.mdcryptography-guide.mdcve-patterns.mdcvss-scoring.mdcwe-top25.mddeserialization-prevention.mderror-message-sanitization.mdfile-upload-security.mdfrontend-security.mdgha-security.mdgit-history-secrets.mdgo-security-features.mdiac-security.mdindistinguishability-defences.mdinput-validation.mdjavascript-typescript-security-features.mdllm-security.mdmodern-attacks.mdnodejs-security-features.mdowasp-top10.mdpath-traversal-prevention.mdphp-security-features.mdpython-security-features.mdDetails
From the project READMESecurity Audit Skill
Security audit patterns (OWASP Top 10, LLM Top 10 2025, CWE Top 25 2025, CVSS v4.0), cloud/IaC, GitHub security. 80+ PHP/TYPO3 checkpoints (v14.3 LTS in typo3-security.md).
Expertise Areas
- Vulnerabilities: XXE, SQLi, XSS, CSRF, command injection, path traversal, file upload, deserialization, SSRF, SSTI, JWT, type juggling
- Standards: OWASP Top 10 / API / LLM (2025), CWE Top 25, CVSS v3.1/v4.0, OWASP ASVS
- Cloud & IaC: AWS; Terraform, Kubernetes, Docker, Helm
- API & Frontend: REST/GraphQL authZ, rate limits, mass assignment, CSP, DOM-XSS
- AI Agents: SKILL.md/AGENTS.md/CLAUDE.md/mcp.json/hooks.json audit; prompt injection; excessive agency
Reference Files (in references/, .md implied)
- Core: owasp-top10, cwe-top25, xxe-prevention, cvss-scoring, api-key-encryption
- Prevention: deserialization-prevention, path-traversal-prevention, file-upload-security, input-validation, error-message-sanitization, ssh-forced-command-hardening
- Architecture: authentication-patterns, security-headers, security-logging, cryptography-guide, security-invariants, indistinguishability-defences
- Language features (
*-security-features): php, python, javascript-typescript, nodejs, go - Frameworks (
*-security): typo3, typo3-fluid, typo3-typoscript, symfony, react, vue - Cloud & IaC: aws-security, iac-security
- API & Frontend: api-security, frontend-security
- AI Agent: llm-security (OWASP LLM Top 10 2025)
- Threats: modern-attacks, cve-patterns
- DevSecOps: ci-security-pipeline, supply-chain-security, automated-scanning, gha-security, git-history-secrets
- Incident: supply-chain-incident-response
Security Checklist
-
semgrep/opengrep,trivy fs --severity HIGH,CRITICAL,gitleaksclean - bcrypt/Argon2 passwords, CSRF on state changes, TLS 1.2+
- Server-side input validation; parameterized SQL; XML entities off
- Output encoding + CSP; no unserialize() on user input
- API keys encrypted; exception messages sanitized
- Secrets out of VCS; audit logging on
- Uploads validated, renamed, outside web root
- Headers HSTS + X-Content-Type-Options; dependencies scanned
GitHub Actions Security
- NEVER interpolate
${{ inputs.* }}/${{ github.event.* }}inrun:— useenv: - Dependency triage: upgrade > override > dismiss. Full patterns:
references/gha-security.md.
Verification
./scripts/security-audit-dispatcher.sh /path/to/project # auto-detect stack
./scripts/security-audit.sh /path/to/project # PHP-only
./scripts/github-security-audit.sh owner/repo # GH repo
Dispatcher detects the stack from indicator files and runs matching scripts/scanners/*.sh (13 ecosystems; see references/ index).
Contributing: https://github.com/netresearch/security-audit-skill