Pentest Script Generator

Pentest Script Generator

Generate professional Python pentest scripts from Strix vuln reports or raw vulnerability descriptions.

Language rule: All skill instructions and generated script code use English. Final summary presented to the user must be in Vietnamese.

🔧 Runtime Scripts

📋 Reference Files

1. Strix vuln-XXXX.md Schema

Parse these fields from the report:

2. Vulnerability Type Detection

Authorization / Access Control

Business Logic

Injection / XSS

SSRF

Account Takeover

Information Disclosure

CORS / Session

3. Auth Detection

4. Test Case Structure

Every pentest script must follow this TC structure:

TC-01: Setup / Get auth token (if needed)
TC-02: Baseline — confirm endpoint works normally
TC-03: Core exploit attempt
TC-04: (Optional) Variation / escalation
TC-05: Control — confirm protected endpoint still enforces
TC-NN: Cleanup — delete/cancel created test data

Verdict Logic

5. Evidence Saving

Every script must save evidence when vulnerabilities are found:

def _save_evidence(data: list[dict], vuln_id: str, label: str, output_dir: str = "."):
    from pathlib import Path
    import csv

    ev_dir = Path(output_dir) / "evidence"
    ev_dir.mkdir(parents=True, exist_ok=True)
    ts = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")

    # JSON
    json_path = ev_dir / f"{vuln_id}_{label}_{ts}.json"
    with open(json_path, "w", encoding="utf-8") as f:
        json.dump(data, f, indent=2, ensure_ascii=False, default=str)

    # CSV (if list of dicts)
    if data and isinstance(data[0], dict):
        csv_path = ev_dir / f"{vuln_id}_{label}_{ts}.csv"
        with open(csv_path, "w", newline="", encoding="utf-8") as f:
            w = csv.DictWriter(f, fieldnames=data[0].keys())
            w.writeheader(); w.writerows(data)

    print(f"  💾 Evidence: {json_path}")

6. File Naming Convention

Save to: vulnerabilities/ subfolder of the project.

7. Verify Script Rules

verify_vulnXXXX.py must be:

• Minimal: 1–3 HTTP requests max
• Fast: Complete in < 10 seconds
• Exit codes: 0 = SAFE, 1 = VULNERABLE, 2 = ERROR
• No dependencies beyond requests

8. Workflow

1. READ   → Parse vuln-XXXX.md (or description/HTTP request)
2. DETECT → Identify vuln type from keywords
3. AUTH   → Identify auth mechanism from PoC
4. WRITE  → Generate pentest_TYPE_vulnXXXX.py
            - Header with metadata
            - Verdict/TestResult classes
            - TC-01..TC-N methods
            - _save_evidence() helper
            - _summary() and _export() helpers
            - main() with argparse (--base-url, --dry-run, --output-dir)
5. WRITE  → Generate verify_vulnXXXX.py (minimal, exit 0/1/2)
6. REPORT → Present final summary to user IN VIETNAMESE

9. Output Summary (always in Vietnamese)

After generating both files, present to user in Vietnamese:

✅ Đã tạo xong cho vuln-XXXX (<tiêu đề>):

  📄 vulnerabilities/vuln-XXXX.md               (Severity: X, CVSS: Y)
  🐍 vulnerabilities/pentest_TYPE_vulnXXXX.py   (N test cases)
  ⚡ vulnerabilities/verify_vulnXXXX.py          (quick verify, exit 0/1/2)

▶  Cách chạy:
   python vulnerabilities/pentest_TYPE_vulnXXXX.py --base-url https://target.com
   python vulnerabilities/verify_vulnXXXX.py --base-url https://target.com

📋 Tóm tắt:
   - Loại lỗ hổng : <TYPE>
   - Auth mechanism: <auth type>
   - Số test cases : N
   - Cleanup       : ✅ included

Anti-Patterns