pentest-engagement-methodology — Claude Code skill for authorized pentests
pentest-engagement-methodology runs an authorized penetration test stage by stage, from scope and engagement rules to the final write-up. Useful when permission is signed and nothing should be missed.
no license 356 installs updated 2026-08-26
npx skills add securityskills/skills --skill pentest-engagement-methodology -a claude-codeWhat pentest-engagement-methodology does
This skill sets the order of work for a permitted penetration test. Scope and engagement rules come first, then reconnaissance, vulnerability analysis, exploitation, post-exploitation and reporting. Every stage says what to gather and what to log, and the box type (black, grey or white) is agreed up front along with test windows and escalation paths.
The guardrails are strict on purpose. No written permission means no testing, each host and domain is checked against the scope document before anything is sent, and destructive actions are off the table. If a target is ambiguous, the agent asks instead of assuming. Deliverables include the test plan, an asset inventory, the findings report, a cleanup log and an agenda for the debrief.
Reports follow a fixed shape: a plain-language summary for stakeholders, then findings with CVSS severity, affected assets, reproduction steps and fixes. Scanner output alone is not evidence. Findings get verified by hand, and the skill ranks them by how exploitable they really are.
What it helps with
- Scope an engagement before a single packet goes out
- Build an asset inventory during reconnaissance
- Verify scanner findings by hand
- Keep an evidence trail for each exploit attempt
- Write the report with severity ratings and reproduction steps
Example prompts for the agent
- Draft the test plan for this scope, including test windows and escalation contacts.
- Check these hosts against the scope document and flag anything ambiguous.
- Turn these notes into a findings report with CVSS severity and remediation advice.
How to install pentest-engagement-methodology
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill pentest-engagement-methodology -a claude-code2Manually: put the files in place
~/.claude/skills/pentest-engagement-methodology/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pentest-engagement-methodology/
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill pentest-engagement-methodology -a codex2Manually: put the files in place
.agents/skills/pentest-engagement-methodology/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add securityskills/skills --skill pentest-engagement-methodology -a cursor2Manually: put the files in place
.cursor/skills/pentest-engagement-methodology/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install securityskills/skills pentest/methodology/pentest-engagement-methodology2Manually: put the files in place
.github/skills/pentest-engagement-methodology/SKILL.md1Skills CLI (Vercel)
npx skills add securityskills/skills --skill pentest-engagement-methodology -a gemini-cli2Platform CLI
gemini skills install https://github.com/securityskills/skills --path pentest/methodology/pentest-engagement-methodologyManually: put the files in place
.devin/skills/pentest-engagement-methodology/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add securityskills/skills --skill pentest-engagement-methodology -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pentest-engagement-methodology
How do I install pentest-engagement-methodology in Claude Code?
Run npx skills add securityskills/skills --skill pentest-engagement-methodology -a claude-code. The skill file lands at ~/.claude/skills/pentest-engagement-methodology/SKILL.md.
What does pentest-engagement-methodology do?
It guides the agent through the phases of an authorized penetration test: scoping, reconnaissance, vulnerability analysis, exploitation, post-exploitation and reporting. Each phase lists what to collect and record.
Can it be used without written authorization?
No. The first hard rule is to confirm written permission, the rules of engagement and emergency contacts before touching anything. The second is to check every target against the scope and ask when unsure.