pentest-social
Skill8 starsChanged 3 months agoMITView on GitHub
Social engineering pentest methodology — phishing strategy, pretexting, vishing scenario, awareness training advisory. No live phishing operation. Triggers on social engineering, phishing, vishing, pretext, awareness, OSINT-driven pretext, GoPhish, Evilginx, phishing simulation.
In this repository63 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-automationSkill
- consultingSkill
- contentSkill
- customer-successSkill
- data-analyticsSkill
- designSkill
- design-tokensSkill
- developmentSkill
- devopsSkill
- ecommerceSkill
- emailSkill
- expo-app-configSkill
- expo-config-pluginSkill
- expo-dev-clientSkill
- expo-eas-buildSkill
- expo-eas-submitSkill
- expo-eas-updateSkill
- expo-modulesSkill
- expo-notificationsSkill
- expo-orchestratorSkill
- expo-prebuildSkill
- expo-routerSkill
- expo-troubleshootingSkill
- financeSkill
- frontend-tasteSkill
- marketingSkill
- market-researchSkill
- mobileSkill
- pentest-adSkill
- pentest-apiSkill
- pentest-bizlogicSkill
- pentest-bugbountySkill
- pentest-cicdSkill
- pentest-cloudSkill
- pentest-credentialsSkill
- pentest-ctfSkill
- pentest-detectionSkill
- pentest-engagementSkill
- pentest-exploit-chainSkill
- pentest-forensicsSkill
- pentest-llmSkill
- pentest-malwareSkill
- pentest-mobileSkill
- pentest-opsec-evidenceSkill
- pentest-orchestratorSkill
- pentest-privescSkill
- pentest-reconSkill
- pentest-reportSkill
- pentest-stigSkill
- pentest-threat-modelSkill
- pentest-webSkill
- pentest-wirelessSkill
- productivitySkill
- productSkill
- salesSkill
- security-checkSkill
- securitySkill
- seo-crawl-budgetSkill
- seoSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 96
This skill does not run any GoPhish command: Only the setup checklist + scenario writing.
- Distinctive: line 129
After the engagement ends:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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-social
Social engineering strategy and awareness training advisory. NO live phishing campaign operation — this skill only does scenario design, target-list scoping, and debrief planning.
Triggers
- "phishing scenario"
- "social engineering plan"
- "pretext idea"
- "vishing scenario"
- "awareness training"
- "gophish setup for a phish simulation"
Engagement Discipline Boundaries
- Proof of authorization required — written client permission, an in-scope user list
- HR + Legal approval — employee targeting is coordinated with HR + Legal
- Employee psychological impact — misuse ends the engagement
- Plan a debrief — post-engagement training material for every target
- Targeting third parties — forbidden (the client provides them)
Phishing Scenario Types
| Type | Example | Impact Measure |
| Mass phish | "Your password is expiring" (generic) | Awareness baseline |
| Spear phish | Personalized (role + name from LinkedIn) | Target role-specific test |
| Whaling | C-level target | High-risk target defense |
| Smishing | Over SMS | Mobile vector |
| Vishing | Phone (impersonate IT support) | Human verification procedure |
| Watering hole | Clone of a site the user visits often | Supply chain |
| QR phish | Physical QR sticker | Hybrid attack |
Pretext Design (Authorized Engagement)
A good pretext = believable + urgency + hard to verify + typical actionExamples:
1. IT Support Pretext
- "Your Office365 account is locked, please verify via this link"
- Believable: common daily email
- Urgency: no account access
- Action: link click + cred input
2. Vendor Invoice Pretext
- "Payment for invoice number X is pending"
- Believable: finance/procurement related
- Urgency: due date passed
- Action: open the attachment (XLSX macro)
3. Internal HR Pretext
- "New performance review system - please log in"
- Believable: internal process
- Hard to verify: HR system change
- Action: cred inputGoPhish Campaign Setup (Setup-Only, No Run)
# config.yml example
admin_server:
listen_url: 127.0.0.1:3333
use_tls: true
phish_server:
listen_url: 0.0.0.0:80
use_tls: falseSetup steps (the user runs manually):
- Prepare GoPhish + landing page
- Sending profile (engagement domain, SPF/DKIM/DMARC test)
- Target list (the list the client provides)
- Template + landing page (clone of the client brand)
- Campaign scheduling (working hours)
This skill does not run any GoPhish command. Only the setup checklist + scenario writing.
Evilginx (Setup-Only)
- Reverse proxy for MFA bypass (within an authorized pentest)
- Setup: phishlet configuration, custom landing page
- Before use: WRITTEN client approval for the MFA-bypass simulation
Vishing (Phone) Scenario
## Vishing Scenario — "IT Helpdesk MFA Reset"
### Preparation
- OSINT: IT team names from LinkedIn
- Social media: organization structure
- Burner phone number + spoofing legal framework (within an authorized pentest)
### Scenario
- "Hi [target name], this is [IT team member name]. There's an issue with our MFA system,
could you read me your confirmation code so I can reset your account?"
- Prepare for pushback questions:
- "Where did you get my number" -> "Helpdesk inventory"
- "Will the director approve" -> "It's urgent, so I skipped that"
### Line
- Keep the conversation under 90 seconds
- Urgency through halting phrasing
- Not asking for creds, asking for the MFA code (push-approval bypass)Debrief / Training Plan
After the engagement ends:
- Aggregate stats: how many clicked, how many gave creds, how many reported
- Feedback — no individual report (shame + retaliation); role-based aggregate
- Training: phishing signs, verification procedures, reporting path
- Test cadence: baseline every 3 months, annual mass campaign
Out-of-Scope
- Live campaign operation (the client does it, or an authorized pentest firm)
- Targeting third parties
- Individual reporting that could become grounds for firing an employee
- Any targeting without HR/Legal approval
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.

