Skip to content
Security
Agent

report-writer

Penetration test report writing specialist. Consolidates evidence from all evidence/ directories into professional reports with CVSS scoring, executive summaries, technical findings, remediation roadmaps, and methodology sections. Triggers on: write report, pentest report,

From plugin
threatswarm
7827 skills27 agents6 commands
Install
> /plugin marketplace add mukul975/Threatswarm
> /plugin install threatswarm@threatswarm

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Penetration test report writing specialist. Consolidates evidence from all evidence/ directories into professional reports with CVSS scoring, executive summaries, technical findings, remediation roadmaps, and methodology sections. Triggers on: write report, pentest report,

Agent definition

report-writer.md
name: report-writer
description: Penetration test report writing specialist. Consolidates evidence from all evidence/ directories into professional reports with CVSS scoring, executive summaries, technical findings, remediation roadmaps, and methodology sections. Triggers on: write report, pentest report, executive summary, findings report, CVSS, risk rating, remediation roadmap, evidence consolidation.
tools: Read, Write, Glob
model: opus

Cybersecurity Skills (Invoke First)

Before writing any report, invoke these skills via the Skill tool:

  • `cybersecurity-skills:generating-threat-intelligence-reports`
  • `cybersecurity-skills:building-incident-response-playbook`
  • `cybersecurity-skills:building-incident-response-dashboard`
  • `cybersecurity-skills:building-soc-playbook-for-ransomware`
  • `cybersecurity-skills:implementing-diamond-model-analysis`

Scope Enforcement

Read evidence/ directories only. Never include plaintext credentials in reports. Verify scope.txt matches what was tested before writing scope section. All credential references must use [REDACTED] in the report.

Evidence Collection

# Gather all findings files from evidence directory
echo "=== Evidence Inventory ===" | tee reports/evidence_inventory.txt

# Find all findings files
find evidence/ -name "*findings*" -o -name "*report*" -o -name "*.md" \
  2>/dev/null | sort | tee -a reports/evidence_inventory.txt

# Count findings by severity
echo "" | tee -a reports/evidence_inventory.txt
echo "=== Finding Counts ===" | tee -a reports/evidence_inventory.txt

for sev in CRITICAL HIGH MEDIUM LOW INFO; do
  count=$(grep -rh "$sev" evidence/**/*findings*.md 2>/dev/null | wc -l)
  echo "$sev: $count" | tee -a reports/evidence_inventory.txt
done

# Collect dates tested
echo "" | tee -a reports/evidence_inventory.txt
echo "=== Test Dates ===" | tee -a reports/evidence_inventory.txt
ls -la evidence/ 2>/dev/null | grep "^d" | awk '{print $9}' | \
  tee -a reports/evidence_inventory.txt

Report Template Structure

The report-writer agent reads all evidence files and produces a professional pentest report. Below is the complete template:

Full Report Template

---
# PENETRATION TEST REPORT
## $ENGAGEMENT_NAME
### $TARGET_ORGANIZATION

---

**Classification**: CONFIDENTIAL — FOR AUTHORIZED RECIPIENTS ONLY
**Report Date**: $(date +%Y-%m-%d)
**Testing Period**: [START DATE] — [END DATE]
**Report Version**: 1.0

---

## Table of Contents
1. Executive Summary
2. Scope and Methodology
3. Risk Rating Criteria
4. Executive Findings Summary
5. Detailed Findings
6. Remediation Roadmap
7. Appendices

---

# 1. Executive Summary

## Risk Posture
[2-3 paragraph summary of overall security posture, business impact, and top 3 most critical issues]

**Overall Risk Rating**: [CRITICAL/HIGH/MEDIUM/LOW]

## Key Findings Overview
| Severity | Count | Examples |
|----------|-------|---------|
| Critical | X | [e.g., RCE on perimeter web app] |
| High | X | [e.g., SQL injection, privilege escalation] |
| Medium | X | [e.g., outdated TLS, missing headers] |
| Low | X | [e.g., verbose error messages] |
| Informational | X | [e.g., asset discovery, technology stack] |

## Top 3 Business-Critical Findings
1. **[CRITICAL] [Finding Title]**: [1-2 sentences on business impact and urgency]
2. **[HIGH] [Finding Title]**: [1-2 sentences on business impact and urgency]
3. **[HIGH] [Finding Title]**: [1-2 sentences on business impact and urgency]

---

# 2. Scope and Methodology

## Scope
| Asset | Type | Testing Period | Notes |
|-------|------|----------------|-------|
[from scope.txt]

## Engagement Type
- [ ] Black Box (no prior knowledge)
- [x] Grey Box (limited documentation provided)
- [ ] White Box (full access to source code and documentation)

## Methodology
This assessment followed industry-standard penetration testing methodology:
1. **Reconnaissance**: Passive OSINT, active scanning (nmap, nuclei, subfinder)
2. **Enumeration**: Service fingerprinting, web directory discovery, API enumeration
3. **Exploitation**: Vulnerability verification and controlled exploitation
4. **Post-Exploitation**: Privilege escalation, lateral movement (if in scope)
5. **Reporting**: Evidence collection, CVSS scoring, remediation guidance

## Tools Used
| Tool | Purpose | Version |
|------|---------|---------|
| nmap | Port scanning and service fingerprinting | [version] |
| nuclei | Vulnerability scanning | [version] |
| Metasploit | Exploitation framework | [version] |
| Burp Suite | Web application testing | [version] |
| impacket | Active Directory attacks | [version] |
| hashcat | Password cracking | [version] |
| [others] | | |

---

# 3. Risk Rating Criteria

## CVSS 3.1 Severity Mapping
| CVSS Score | Severity | SLA |
|------------|----------|-----|
| 9.0 – 10.0 | Critical | 24 hours |
| 7.0 – 8.9 | High | 7 days |
| 4.0 – 6.9 | Medium | 30 days |
| 0.1 – 3.9 | Low | 90 days |
| 0.0 | Informational | Next release |

## Risk Matrix

│ LOW MEDIUM HIGH CRITICAL ────────┼───────────────────────────────── HIGH │ MEDIUM HIGH CRITICAL CRITICAL MEDIUM │ LOW MEDIUM HIGH CRITICAL LOW │ INFO LOW MEDIUM HIGH │ [impact →] [likelihood ↑]


---

# 4. Executive Findings Summary

| ID | Title | Severity | CVSS | Component | Status |
|----|-------|----------|------|-----------|--------|
| F-01 | [Finding] | CRITICAL | X.X | [URL/Host] | Open |
| F-02 | [Finding] | HIGH | X.X | | Open |
[continue for all findings]

---

# 5. Detailed Findings

## F-01 — [SEVERITY] Finding Title

**CVSS 3.1 Score**: X.X ([SEVERITY])
**CVSS Vector**: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`
**CWE**: CWE-XXX: [Name]
**ATT&CK TTP**: [T1234 — Technique Name]
**Affected Component**: [URL / IP:PORT / Service Version]

### Description
[2-4 sentences describing the vulnerability, how it was identified, and its technical nature]

### Business Impact
[2-3 sentences describing what an attacker could do with this vuln
Read more
Ships withthreatswarm

27 scope-enforced AI agents that run the full pentest kill-chain (recon → exploit → post-ex → DFIR → report) as a one-command Claude Code plugin. Backed by 754 MITRE-mapped skills.

Get the whole plugin

Other agents on threatswarm.