Pwp Security Audit

Security Audit Skill

This skill defines how to perform a security-focused code review. Security changes have high blast radius — always flag findings and get explicit approval before making fixes.

Security Mindset

• Assume all input is hostile. User input, API responses, URL parameters, cookies, headers — all untrusted until validated.
• Defense in depth. Never rely on a single layer of protection. Validate on client AND server.
• Least privilege. Give code, users, and services only the permissions they need. Nothing more.
• Flag, don't fix (without approval). Security changes can break auth flows, lock users out, or introduce regressions. Always get approval first.

Security Review Checklist

1. Secrets & Credentials

• No API keys, tokens, or passwords in source code
• No secrets in client-side bundles
• .env files are in .gitignore
• .env.example exists with placeholder values (no real secrets)
• No secrets in commit history
• Server-side environment variables used for sensitive config

2. Input Validation & Sanitization

• All user input validated on the server (not just client-side)
• HTML output sanitized to prevent XSS (no dangerouslySetInnerHTML with user data)
• SQL queries use parameterized statements (no string concatenation)
• File uploads validated (type, size, content — not just extension)
• URL parameters and query strings validated before use
• JSON payloads validated against expected schema

3. Authentication

• Passwords hashed with bcrypt/argon2 (never MD5/SHA1, never plaintext)
• Session tokens are cryptographically random and sufficiently long
• JWT tokens have expiration and are validated on every request
• Password reset tokens are single-use and time-limited
• Rate limiting on login endpoints (prevent brute force)
• Failed login attempts logged (for detection)

4. Authorization

• Every API endpoint checks user permissions (server-side)
• UI hiding is NOT the only access control
• Resource access checks ownership (user can only access their own data)
• Admin routes require admin role verification on every request
• CORS configured to allow only trusted origins

5. Data Protection

• HTTPS enforced (no mixed content)
• Sensitive data not logged (passwords, tokens, PII)
• Sensitive data not in URL parameters
• Database connections use TLS
• PII handling complies with relevant regulations (GDPR, CCPA)

6. Dependencies

• npm audit shows no critical or high vulnerabilities
• Dependencies are from trusted sources (no typosquatting)
• Lock file is committed and up to date
• No dependencies with known CVEs in production

7. Error Handling

• Error messages don't leak internal details (stack traces, file paths, SQL queries)
• Custom error pages for 4xx and 5xx (no framework defaults)
• Errors are logged server-side for debugging
• API errors return consistent, safe error shapes

OWASP Top 10 Quick Reference

Reporting Format

## Security Finding: {title}

**Severity:** Critical | High | Medium | Low
**Category:** {OWASP category or custom}
**Location:** {file:line}

**Description:** What the vulnerability is and why it matters.
**Recommendation:** Specific fix with code suggestion.
**Blast Radius:** What else might be affected by the fix.

Rules

1. Never commit secrets — even for testing. Use environment variables.
2. Never weaken security for convenience — no disabling CORS, no skipping auth.
3. Flag findings, don't auto-fix — security changes need human review.
4. Don't guess at security — if unsure, flag it as a question.
5. Redact sensitive data — never include real credentials in plans or communication.