ワンクリックで
pentest-report
Generate professional penetration testing reports from findings
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Generate professional penetration testing reports from findings
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
API security testing — REST, GraphQL, authentication, authorization, rate limiting, business logic
Network penetration testing — service enumeration, vulnerability scanning, credential auditing, Active Directory
Master pentest orchestration — full pipeline from target to report with confirmation gates
Comprehensive reconnaissance — passive OSINT, subdomain enumeration, port scanning, technology fingerprinting
Web application penetration testing — XSS, SQLi, CSRF, SSRF, command injection, file upload, WAF bypass
Code security testing — SAST, SCA, secret detection, container scanning, IaC analysis
| name | pentest_report |
| description | Generate professional penetration testing reports from findings |
Generate structured, professional vulnerability reports from pentest findings.
Generate markdown report convertible to PDF. Structure follows PTES/OWASP standards.
# Penetration Test Report
## Engagement Details
- **Client:** {client_name}
- **Target:** {target}
- **Date:** {start_date} — {end_date}
- **Tester:** Hermes Agent (Athena Pentest)
- **Scope:** {scope_description}
## Executive Summary
{2–3 paragraph non-technical summary of findings, risk level, key recommendations}
### Risk Overview
| Severity | Count |
|----------|-------|
| Critical | {n} |
| High | {n} |
| Medium | {n} |
| Low | {n} |
| Info | {n} |
## Methodology
{Recon → Enumeration → Vulnerability Scanning → Exploitation → Reporting}
## Findings
### CRITICAL-001: {Title}
- **Severity:** Critical
- **CVSS Score:** {score}
- **Affected:** {endpoint/host/port}
- **Description:** {what was found}
- **Evidence:** {command output, curl reproduction, screenshot reference}
- **Impact:** {business impact — data breach, RCE, etc.}
- **Remediation:** {specific fix steps}
- **References:** {CVE, CWE, OWASP link}
[Repeat for HIGH, MEDIUM, LOW...]
## Network Summary
### Open Ports & Services
| Host | Port | Service | Version | Notes |
|------|------|---------|---------|-------|
## Web Application Summary
### Endpoints Tested
- Total endpoints: {n}
- Vulnerable endpoints: {n}
### Vulnerabilities by OWASP Category
| Category | Found | Severity |
|----------|-------|----------|
## Recommendations
### Immediate (Critical/High)
1. {action item}
### Short-term (Medium)
1. {action item}
### Long-term (Low/Info)
1. {action item}
## Appendix
- Tool output summaries
- Evidence file list
- Wordlists used
- Scope confirmation
Before generating, collect all findings:
find /tmp/pentest/{target}/ -name "*.txt" -o -name "*.json" -o -name "*.md" | sort
cat /tmp/pentest/{target}/nuclei-*.txt
cat /tmp/pentest/{target}/nmap-*.nmap
cat /tmp/pentest/{target}/web-findings.md
cat /tmp/pentest/{target}/network-findings.md
Aggregate into /tmp/pentest/{target}/findings.json using the aggregate-results.sh script.
| Severity | Criteria |
|---|---|
| Critical | RCE, SQLi with data access, auth bypass, unauthenticated admin |
| High | Stored XSS, SSRF with internal access, privilege escalation, sensitive data exposure |
| Medium | Reflected XSS, CSRF on important functions, weak password policy, missing security headers |
| Low | Information disclosure, verbose errors, missing rate limiting |
| Info | Best practice recommendations, theoretical findings |
pandoc report.md -o report.pdf --pdf-engine=wkhtmltopdf
/tmp/pentest/{target}/report-{date}.md/tmp/pentest/{target}/evidence-{date}.tar.gz/tmp/pentest/{target}/findings.json