Skip to content
Security
Command

/recon

Map the attack surface of an authorized target.

From plugin
claude-pentest-skills
406 skills3 agents6 commands
Install
$ npx -y skills add frendysanusi/claude-pentest-skills --agent claude-code

How it fires

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

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/recon

Context preview

What this command does when you run it.

Map the attack surface of an authorized target.

Command definition

recon.md

/recon <target>

Map the attack surface of an authorized target.

Usage

/recon example.com
/recon https://app.example.com

Preconditions

1. **Scope must exist.** Check for `engagements/<target>/scope.md`. If not found:

  • Display: "No scope defined for `<target>`. Run `/scope <target>` first."
  • **Stop.**

2. **Verify target matches scope.** The target must be listed as in-scope.

Procedure

Step 1: Load Agent and Skill

1. Load `agents/recon-agent.md` — Adopt the Recon Agent persona 2. Load `skills/recon.md` — Reconnaissance methodology

Step 2: Load Current State

Read engagement state files:

  • `engagements/<target>/scope.md` — Scope boundaries and constraints
  • `engagements/<target>/tech-stack.md` — Any previously identified technologies
  • `engagements/<target>/coverage.md` — Any previously completed recon
  • `engagements/<target>/notes.md` — Any prior observations

If recon was partially completed before, resume from where it left off (check coverage.md).

Step 3: Execute Recon Phases

Follow `skills/recon.md` phases 1 through 5:

1. **Technology Fingerprinting** → Update `tech-stack.md` 2. **Endpoint Discovery** → Update `coverage.md` endpoint table 3. **Input Vector Mapping** → Update `coverage.md` with input vectors per endpoint 4. **Authentication Mechanism ID** → Update `tech-stack.md` auth section 5. **Infrastructure & WAF Detection** → Update `tech-stack.md` CDN/WAF section

Step 4: Produce Recon Summary

Generate the structured recon summary as defined in `skills/recon.md`:

  • Attack surface overview
  • High-value targets
  • Recommended hunt order

Step 5: Update State

  • Mark WSTG-INFO categories as tested in `coverage.md`
  • Add any notable observations to `notes.md`
  • Confirm all state files are updated

Step 6: Next Steps

Suggest the next command:

Recon complete for <target>.
Discovered <X> endpoints, <Y> input vectors.
Tech stack: <summary>

Suggested next step: /hunt <recommended-vuln-class>

Resuming Partial Recon

If the user runs `/recon` again on a target with existing recon data: 1. Show what phases are already complete 2. Ask: "Resume from Phase X, or start fresh?" 3. If resuming, skip completed phases 4. If starting fresh, clear and rebuild state files (confirm with user first)

Read more
Ships withclaude-pentest-skills

AI-powered web application penetration testing skills with Claude Code

Get the whole plugin
Stats
41
Stars
7
Forks
Active
Maintenance
Python
Language
3d ago
Last commit
5mo ago
Created

Repo: frendysanusi/claude-pentest-skills

Other commands on claude-pentest-skills.