Status: Stable
Version: 1.0.0
Author: Rifteo
Tags: pentest, reporting, security
Summary
Turn all confirmed findings from a testing engagement into a single, client-ready penetration test report covering executive summary through technical appendices.- Generates a cover page, executive summary (written for C-suite, no jargon), scope and methodology section, risk summary table ordered by severity, and full technical findings in
finding-writerformat - Pulls from confirmed findings,
ENGAGEMENT.md, and scope details asks for missing information (test dates, tester name) rather than inventing it - Executive summary is written for a non-technical audience: what was tested, overall risk posture in plain language, the single most critical finding in business terms, and top 3 recommended actions
- Recommendations summary cross-references finding IDs (F-01, F-02…) with immediate, medium, and hardening actions ordered by severity
SKILL.md file
Discover skill details
Discover skill details
Pentest Report Generator
Turn all findings from a testing engagement into a single, client-ready penetration test report. Auditors spend 30–40% of engagement time on reporting. This skill handles the structure, ordering, and framing you provide the findings.When to Use This Skill
Use this skill when the user:- Says “generate the report”, “write the report”, “produce the deliverable”
- Is at the end of an engagement and all findings are confirmed and written up
- Wants a draft report to review before sending to the client
What You Need Before Starting
- Confirmed findings (from
finding-writer) - Engagement scope and target (from
ENGAGEMENT.mdorscope-grilloutput) - Test dates and tester names (asked for if not available)
How It Works
Section 1: Cover PageClient name, engagement title, date range, classification (Confidential), prepared by.Section 2: Executive Summary3–5 paragraphs written for a non-technical audience (C-suite, board):- What was tested and why
- Overall risk posture in plain language
- The single most critical finding, in business terms
- Top 3 recommended actions
| # | Title | Severity | Component | Status |
|---|---|---|---|---|
| F-01 | SQL Injection in /api/search | Critical | API | Confirmed |
finding-writer format: Title, Severity, CVSS, Description, Evidence, Impact, Recommendation, References.Section 6: Recommendations SummaryOrdered action list immediate (Critical/High) first, then Medium, then hardening. Cross-references finding IDs.Section 7: Appendices (if applicable)Full tool output, scope confirmation letter reference, methodology references.Output
A complete, client-ready penetration test report in markdown format, ready for conversion to PDF or Word.Known Limitations
- The executive summary must be understandable by someone with no security background
- Never includes unconfirmed findings suspected issues are marked “Requires Further Testing”
- Every finding in the report must have a corresponding ID in the risk table
- No generic security advice unrelated to the engagement
Benchmark Results
Tested on claude-sonnet-4-6 via Claude Code CLI. Same prompt, same model, same target. The only variable is whether the skill is loaded.| Metric | Without Skill | With Skill |
|---|---|---|
| Turns to complete | 1 | 1 |
| Response tokens | ~7,144 | ~5,444 |
| Total time | 128s | 100s |
Related skills
finding-writer
Convert raw pentest notes into structured audit findings ready for reporting
scope-grill
Interviews the user about a pentest engagement before any testing begins
engagement-handoff
Documents the current engagement state so the next session can continue without losing context

