Agent skill

recon

Quellcode ansehen: coreyhaines31/cybersecurity-skills

#124Globales Ranking · von 124 SkillsCritical

Installation

npx skills add coreyhaines31/cybersecurity-skills --skill recon

33

Installationen

EU-hosted inference API

Power your AI agent skills with open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

MiniMax

MiniMax M3

$0.50 / $1.90

per M tokens

Z.ai

GLM 5.3 Flash

$0.20 / $0.60

per M tokens

MoonshotAI

Kimi K3

$4.00 / $18.00

per M tokens

DeepSeek

DeepSeek V4.1 Flash

$0.40 / $1.42

per M tokens

Recon — Penetration Testing Reconnaissance

Perform structured reconnaissance against an authorized target, organizing findings into an actionable attack surface map.

Authorization Check

Before running any commands, confirm:

  1. The user has written authorization for the target (pentest engagement, bug bounty program, CTF/lab environment)
  2. The target is within the defined scope

If authorization is unclear, ask before proceeding. Never assume authorization.

Methodology

Phase 1: Passive Recon

Gather information without touching the target directly.

DNS enumeration:

  • Run dig any $ARGUMENTS for A, AAAA, MX, TXT, NS, CNAME records
  • Attempt zone transfer: dig axfr @ns-server $ARGUMENTS
  • Enumerate subdomains via certificate transparency:
    curl -s "https://crt.sh/?q=%25.$ARGUMENTS&output=json" | jq -r '.[].name_value' | sort -u

WHOIS and registration: Run whois $ARGUMENTS for registrant, nameserver, and creation date info.

Search engine dorking: Use targeted queries — site:, inurl:, filetype:, intitle: — to find exposed pages, documents, and admin panels.

Technology fingerprinting: Identify frameworks, CMS, server software, and JavaScript libraries from public-facing pages.

Public code repositories: Search GitHub/GitLab for the target's org name, domain, API keys, or internal paths.

Historical data: Check the Wayback Machine for old endpoints, removed pages, and configuration files.

Phase 2: Active Recon (explicit authorization only)

Port scanning:

nmap -sC -sV -oN scan-results.txt $ARGUMENTS

Start with top 1000 ports. Expand to full range (-p-) if needed. Use -Pn if the host appears down but is in scope.

Service enumeration: Based on open ports, probe for version info and default configurations.

Web content discovery:

  • Directory bruting with gobuster, feroxbuster, or dirsearch
  • Virtual host enumeration
  • API endpoint discovery (check /api/, /v1/, /graphql, /swagger.json)

SSL/TLS analysis: Run testssl.sh or sslyze to check for weak ciphers, expired certificates, and misconfigurations.

Phase 3: Analysis

Correlate all findings. Identify the most promising attack vectors and prioritize by:

  1. Severity of potential impact
  2. Likelihood of exploitation
  3. Exposure level (internet-facing vs. internal)

Output Format

Produce a structured recon report:

# Recon Report
## Target: [target]
## Scope: [confirmed scope]
## Date: [date]

### Passive Findings
| Finding | Details | Relevance |
|---------|---------|-----------|

### Subdomains Discovered
- [list]

### Technologies Detected
- [list with versions where identified]

### Active Findings
| Port | Service | Version | Notes |
|------|---------|---------|-------|

### Attack Surface Summary
[Prioritized list of interesting findings with risk assessment]

### Recommended Next Steps
[Ordered list of what to investigate further]

Boundaries

  • Stay within the defined scope — never scan adjacent or out-of-scope systems
  • Rate-limit aggressive scans to avoid disruption
  • Log all commands run for the engagement record
  • If you discover evidence of active compromise by a third party, alert the user immediately
  • Refuse requests targeting systems without explicit authorization
  • Refuse requests for mass scanning of unrelated targets

References

  • PTES (Penetration Testing Execution Standard)
  • OWASP Testing Guide
  • Bug Bounty Methodology (jhaddix/tbhm)

So verwenden Sie diesen Skill

  1. 1

    Install recon by running npx skills add coreyhaines31/cybersecurity-skills --skill recon in your project directory. Führen Sie den obigen Installationsbefehl in Ihrem Projektverzeichnis aus. Die Skill-Datei wird von GitHub heruntergeladen und in Ihrem Projekt platziert.

  2. 2

    Keine Konfiguration erforderlich. Ihr KI-Agent (Claude Code, Cursor, Windsurf usw.) erkennt installierte Skills automatisch und nutzt sie als Kontext bei der Code-Generierung.

  3. 3

    Der Skill verbessert das Verständnis Ihres Agenten für recon, und hilft ihm, etablierte Muster zu befolgen, häufige Fehler zu vermeiden und produktionsreifen Code zu erzeugen.

Was Sie erhalten

Skills sind Klartext-Anweisungsdateien — kein ausführbarer Code. Sie kodieren Expertenwissen über Frameworks, Sprachen oder Tools, das Ihr KI-Agent liest, um seine Ausgabe zu verbessern. Das bedeutet null Laufzeit-Overhead, keine Abhängigkeitskonflikte und volle Transparenz: Sie können jede Anweisung vor der Installation lesen und prüfen.

Kompatibilität

Dieser Skill funktioniert mit jedem KI-Coding-Agenten, der das skills.sh-Format unterstützt, einschließlich Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider und anderen Tools, die projektbezogene Kontextdateien lesen. Skills sind auf Transportebene framework-agnostisch — der Inhalt bestimmt, für welche Sprache oder welches Framework er gilt.

Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.