vibeeval/pentest-methodology

Pentest Methodology

Etik guvenlik testi metodolojisi. Shannon framework'unden adapte.

ONEMLI: Bu skill sadece YETKILI guvenlik testleri icin kullanilir. Bug bounty, pentest anlasmasi, veya kendi sisteminiz olmali.

5-Faz Pipeline

Phase 1: Recon ──▶ Phase 2: Vuln Analysis ──▶ Phase 3: Exploitation
                                                        │
Phase 5: Report ◀── Phase 4: Verification ◀────────────┘

Phase 1: Reconnaissance (Kesfetme)

| Adim | Arac/Yontem | Cikti | |------|-------------|-------| | Subdomain enum | DNS brute, certificate transparency | Subdomain listesi | | Port scan | nmap, masscan | Acik portlar | | Tech stack | Wappalyzer, HTTP headers | Teknoloji listesi | | Directory enum | ffuf, gobuster | Endpoint listesi | | API discovery | Swagger/OpenAPI, sitemap | API endpoint'leri | | Source review | JS dosyalari, comments | Hardcoded info |

Phase 2: Vulnerability Analysis

OWASP Top 10 kontrol matrisi:

| # | Vuln | Test Yontemi | |---|------|-------------| | A01 | Broken Access Control | IDOR, privilege escalation, path traversal | | A02 | Cryptographic Failures | SSL config, weak ciphers, plaintext storage | | A03 | Injection | SQLi, XSS, command injection, template injection | | A04 | Insecure Design | Business logic flaws, race conditions | | A05 | Security Misconfiguration | Default creds, verbose errors, CORS | | A06 | Vulnerable Components | CVE scan, outdated dependencies | | A07 | Auth Failures | Brute force, session fixation, JWT attacks | | A08 | Data Integrity | Deserialization, CI/CD pipeline attacks | | A09 | Logging Failures | Log injection, insufficient audit trail | | A10 | SSRF | Internal service access, cloud metadata |

Phase 3: Exploitation (Dogrulama)

Her bulgu icin:

1. Reproduce: Tekrarlanabilir adimlar yaz
2. Proof: Etkiyi goster (ekran goruntusu, response)
3. Impact: Gercek etki ne? (Data leak, RCE, account takeover)
4. Scope: Etki alani ne kadar genis?

Phase 4: Verification

Bulgunun gercek oldugunu dogrula:

• False positive degil mi? Farkli kosullarda tekrarla
• Scope dogru mu? Sadece bir endpoint mi, yoksa sistemik mi?
• Severity dogru mu? Etkiyi abartma, kucumseme

Phase 5: Report

Yapilandirilmis bulgu formati (asagida)

Proof Levels

| Level | Tanim | Ornek | |-------|-------|-------| | L1 - Theoretical | Potansiyel risk, exploit edilmemis | "Bu endpoint input validate etmiyor" | | L2 - Demonstrated | Bypass/leak gosterildi | "SQL injection ile hata mesaji leak etti" | | L3 - Exploited | Tam exploit, veri erisimi | "Admin panel'e yetkisiz erisim saglandi" | | L4 - Chained | Birden fazla vuln zincirlendi | "XSS + CSRF = Account takeover" |

Structured Finding Format

## [SEVERITY] Finding Title

**ID**: FINDING-001
**Severity**: Critical / High / Medium / Low / Informational
**Proof Level**: L1 / L2 / L3 / L4
**CVSS**: X.X (hesapla: cvss.org)
**CWE**: CWE-XXX

### Description
Ne bulundu, tek paragraf.

### Impact
Exploit edilirse ne olur?

### Steps to Reproduce
1. [Adim 1]
2. [Adim 2]
3. [Adim 3]

### Proof
[Screenshot, HTTP request/response, veya kod]

### Remediation
Nasil duzeltilir?

### References
- [OWASP link]
- [CWE link]

Source-to-Sink Taint Tracing

Kullanici input'unun tehlikeli bir fonksiyona ulasip ulasamadigini kontrol et:

Source (Input)        ──▶  Transform/Sanitize?  ──▶  Sink (Tehlikeli fonksiyon)
req.body.username     ──▶  Validation var mi?    ──▶  db.query(...)
req.query.redirect    ──▶  URL whitelist var mi?  ──▶  res.redirect(...)
req.headers.host      ──▶  Sanitize var mi?      ──▶  fetch(...)

Source'lar: req.body, req.query, req.params, req.headers, cookies, file uploads Sink'ler: SQL query, eval(), exec(), redirect(), innerHTML, dangerouslySetInnerHTML

Agent Entegrasyonu

• security-analyst: Bu pipeline'i kullanarak tam guvenlik auditi yapar
• security-reviewer: Code review sirasinda vuln pattern'lerini kontrol eder
• code-reviewer: Security-relevant code degisikliklerinde flag kaldirir

Kurallar

• Yetki olmadan test YAPMA
• Rate limiting'e uy, sistemi cokertme
• Buldugun seyi raporla, exploit etme (beyond PoC)
• Hassas verileri rapordan cikar (maskeleme)
• Remediation onerisi ZORUNLU