pentest-report
Skill37 starsChanged 5 months agoMITView on GitHub
Generates a complete, client-ready penetration test report from all findings in the current engagement executive summary, risk table, technical findings, and recommendations. Trigger when the user says "generate the report", "write the report", or "produce the deliverable", is at the end of an engagement with all findings confirmed and written up, or wants a draft report to review before sending to the client.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- KonstiJo/pentest-report-skilltheir own version, first seen Jun 26, 2026
- hackingyseguridad/IAtheir own version, first seen Jun 19, 2026
- crazyMarky/pentest-skillstheir own version, first seen Mar 5, 2026
- aakash-dhar/claude-skillstheir own version, first seen Feb 19, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- crazyMarky/pentest-skills★ 301same name
- hackingyseguridad/IA★ 3same name
- aakash-dhar/claude-skills★ 0same name
- KonstiJo/pentest-report-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository38 other files it gives its agents.
- ad-breachSkill
- ai-llm-hunterSkill
- attack-surfaceSkill
- bugbounty-reporterSkill
- cavemanSkill
- check-exploitSkill
- clickjacking-hunterSkill
- compliance-gap-analyzerSkill
- control-lookupSkill
- ctf-writeupSkill
- cvss-scorerSkill
- deadangleSkill
- droid-reconSkill
- economist-attackSkill
- engagement-handoffSkill
- finding-writerSkill
- find-skillsSkill
- graphql-raiderSkill
- hexstrike-forgeSkill
- high-severity-hunterSkill
- hpp-hunterSkill
- idor-hunterSkill
- js-analyzerSkill
- jwt-crackerSkill
- less-aggressive-attackSkill
- less-noise-attackSkill
- nuclei-template-writerSkill
- redirect-forgeSkill
- redmindSkill
- remediation-plannerSkill
- risk-assessorSkill
- scope-grillSkill
- skill-benchmarkSkill
- ssrf-hunterSkill
- ssti-hunterSkill
- vuln-diagnoseSkill
- xss-hunterSkill
- xxe-phantomSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Test dates and tester names (ask if not available)
- Very specific: line 35
Do not use technical jargon.
- Very specific: line 40
Test type (black/grey/white box)
- Distinctive: line 72
Never include unconfirmed findings — mark suspected issues as "Out of Scope" or "Requires Further Testing"
- Distinctive: line 73
Every finding in the report must have a corresponding ID in the risk table
- Distinctive: line 74
Do not pad with generic security advice unrelated to the engagement
- Distinctive: line 75
Ask for test dates and tester name if ENGAGEMENT.md is missing
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
What You Need Before Starting
- Confirmed findings (from
finding-writer) - Engagement scope and target (from
ENGAGEMENT.mdorscope-grilloutput) - Test dates and tester names (ask if not available)
Report Structure
Generate each section in order. See references/report-template.md for the full template.
1. Cover Page
Client name, engagement title, date range, classification (Confidential), prepared by.
2. Executive Summary
3-5 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
Do not use technical jargon. Do not list every finding. See references/exec-summary-guide.md.
3. Scope and Methodology
- In-scope targets (from ENGAGEMENT.md)
- Out-of-scope items
- Test type (black/grey/white box)
- Test dates
- Tools and techniques used (high level)
- Limitations and caveats
4. Risk Summary Table
| # | Title | Severity | Component | Status |
| F-01 | SQL Injection in /api/search | Critical | API | Confirmed |
Order by severity (Critical → High → Medium → Low → Info).
5. Technical Findings
One section per finding, in the same order as the risk table. Each finding uses the full finding-writer format:
Title, Severity, CVSS, Description, Evidence, Impact, Recommendation, References.
6. Recommendations Summary
Ordered action list — immediate (Critical/High) first, then Medium, then hardening. Cross-reference finding IDs (F-01, F-02...).
7. Appendices (if applicable)
- Full tool output
- Scope confirmation letter reference
- Methodology references
Rules
- The executive summary must be understandable by someone with no security background
- Never include unconfirmed findings — mark suspected issues as "Out of Scope" or "Requires Further Testing"
- Every finding in the report must have a corresponding ID in the risk table
- Do not pad with generic security advice unrelated to the engagement
- Ask for test dates and tester name if ENGAGEMENT.md is missing
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.