Recon Osint logo

Recon Osint

Community
hypnguyen1209
recon-osint

Use when mapping a target's external attack surface or gathering OSINT — subdomain enumeration, attack-surface mapping (httpx/katana/JS secrets), subdomain takeover, multi-cloud/Azure tenant recon, GitHub secret dorking, breach/infostealer credential intel, CVE prioritization (EPSS/KEV)

Overview

Publisherhypnguyen1209
Repositoryoffensive-claude
Skill namerecon-osint
Stars
396
Forks
71
Bundled files
14
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 14 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hypnguyen1209 on GitHub. Read the source before you install it.

Installation

Install the Recon Osint AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hypnguyen1209/offensive-claude/tree/main/skills/recon-osint
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hypnguyen1209/offensive-claude.git /tmp/offensive-claude
mkdir -p .claude/skills
cp -r /tmp/offensive-claude/skills/recon-osint .claude/skills/recon-osint
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Recon Osint in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Recon Osint on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Recon Osint is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Reconnaissance & OSINT

When to Activate

  • A new engagement begins and you need a full external attack-surface map for a set of root domains / ASNs.
  • Expanding scope: pivoting from one discovered asset (subdomain, IP block, cloud account) to the rest of the estate.
  • Hunting dangling DNS / subdomain-takeover candidates, including S3 buckets referenced by CI/CD assets.
  • Building a target profile for social engineering / initial access (emails, usernames, breach + infostealer exposure).
  • Discovering leaked secrets in public GitHub/GitLab orgs and exposed cloud storage.
  • Triaging which discovered CVEs actually matter (KEV + EPSS + exposure) before weaponization.

Technique Map

TechniqueATT&CKCWEReferenceScript
Passive subdomain enum (subfinder/amass/CT logs)T1590.002, T1596.001CWE-200references/subdomain-discovery.mdscripts/recon_orchestrator.py
DNS brute / permutation / resolution (puredns/alterx/dnsx)T1595.002, T1590.002CWE-200references/subdomain-discovery.mdscripts/recon_orchestrator.py
ASN → CIDR → reverse-DNS expansionT1590.005, T1596.005CWE-200references/subdomain-discovery.mdscripts/recon_orchestrator.py
HTTP probing + tech fingerprint (httpx)T1595.002, T1592.002CWE-200references/attack-surface-mapping.mdscripts/recon_orchestrator.py
Headless crawling + archive URLs (katana/gau)T1595.002, T1593.003CWE-200references/attack-surface-mapping.mdscripts/js_secret_hunter.py
JavaScript endpoint / secret extractionT1593.003, T1552.001CWE-540references/attack-surface-mapping.mdscripts/js_secret_hunter.py
Subdomain takeover (dangling CNAME/NS)T1583.001, T1584.001CWE-350references/subdomain-takeover.mdscripts/subdomain_takeover.py
Deleted-S3 takeover → supply-chain pivotT1583.001, T1195.002CWE-350references/subdomain-takeover.mdscripts/subdomain_takeover.py
Multi-cloud bucket/blob enum (cloud_enum)T1580, T1596.005CWE-732references/cloud-saas-recon.mdscripts/cloud_asset_enum.py
Azure tenant outsider recon (AADInternals)T1590.001, T1589CWE-200references/cloud-saas-recon.mdscripts/cloud_asset_enum.py
GitHub/GitLab dorking + secret scanningT1593.003, T1213.003CWE-540references/cloud-saas-recon.mdscripts/cloud_asset_enum.py
Email/username harvesting (theHarvester)T1589.002, T1591CWE-200references/breach-credential-intel.mdscripts/breach_intel.py
Breach + infostealer credential intel (HIBP/DeHashed)T1589.001, T1596CWE-522references/breach-credential-intel.mdscripts/breach_intel.py
CVE enrichment + prioritization (NVD/EPSS/KEV)T1592.002, T1596CWE-1395references/cve-exploit-intel.mdscripts/cve_prioritizer.py
Shodan InternetDB exposure → CVE mappingT1596.005, T1595.002CWE-200references/cve-exploit-intel.mdscripts/cve_prioritizer.py

Quick Start

bash
export DOMAIN=target.com
# 0. Validate resolvers once (puredns needs a clean list)
dnsvalidator -tL https://public-dns.info/nameservers.txt -threads 100 -o resolvers.txt

# 1. Full discovery + probe + crawl + takeover + nuclei, JSONL out (see orchestrator)
python3 scripts/recon_orchestrator.py -d $DOMAIN -o out/ --resolvers resolvers.txt --nuclei

# 2. JS/endpoint + secret hunting over live hosts
python3 scripts/js_secret_hunter.py -l out/httpx_live.txt -o out/js/

# 3. Dangling-DNS / subdomain-takeover triage
python3 scripts/subdomain_takeover.py -l out/all_subdomains.txt -o out/takeovers.jsonl

# 4. Cloud + code recon (buckets, Azure tenant, GitHub secrets)
python3 scripts/cloud_asset_enum.py -k $DOMAIN --company target --azure-domain $DOMAIN --gh-org target

# 5. People + breach/infostealer intel
python3 scripts/breach_intel.py --domain $DOMAIN --harvest --hibp --dehashed

# 6. Triage CVEs from fingerprints → KEV/EPSS/exposure ranked
python3 scripts/cve_prioritizer.py --from-httpx out/httpx_live.txt --ip-file out/ips.txt -o out/cve_ranked.jsonl

OPSEC & Detection (summary)

TechniqueTelemetry / IOCDetection (Sigma/EDR)OPSEC note
Passive enum (CT/API)None on target; queries hit 3rd-party APIsTarget cannot see it; CT-log monitoring (certstream) detects new certs onlyFully passive — prefer for stealth; no target traffic
DNS brute / resolutionBurst of NXDOMAIN/A queries to authoritative + resolversDNS firewall: high-volume distinct-label rate per source IP; Zeek dns.cc/NXDOMAIN ratioThrottle -rate, rotate resolvers, never brute a single auth NS directly
httpx / katana probingSpike of HTTP(S) requests, odd UA, favicon/JARM fetchesWAF/CDN: request-rate + UA anomaly; access-log User-Agent: *httpx*/*katana*Set custom UA, low -rl, route via proxy pool / cloud egress
Subdomain takeover checkHTTP GET to dangling host (lands on 3rd-party)3rd-party provider logs; CT for new cert on claimed hostVerify with passive fingerprint before any claim; claiming is loud
Cloud bucket enumDNS + HTTP to *.s3/blob/storage.googleapisCloud provider access logs; GuardDuty Discovery:S3/*Hits provider, not target; still rate-limited / loggable
Azure tenant reconRequests to login.microsoftonline.comEntra sign-in/audit logs do not see unauth realm probesgetuserrealm/OpenID are unauth & invisible to tenant
GitHub/GitLab dorkingAPI/search queries from your tokenGitHub audit log (only org members'); secret-scanning alertsUse a throwaway token; respect rate limits to avoid bans
Breach/infostealer lookup3rd-party API calls (HIBP/DeHashed)None on targetHandle PII per ROE/GDPR; document lawful basis
CVE enrichmentNVD/EPSS/KEV/Shodan API callsNone on targetMap exposure to in-scope assets only

Deep Dives

  • references/subdomain-discovery.md — Passive sources + CT logs, puredns/massdns resolution, alterx permutations, ASN→CIDR→PTR expansion, wildcard handling.
  • references/attack-surface-mapping.md — httpx enrichment (-td -favicon -jarm -asn), katana headless/authenticated crawling, gau/wayback archive mining, JS endpoint + secret extraction, nuclei triage of the live set.
  • references/subdomain-takeover.md — Dangling-DNS theory, can-i-take-over-xyz fingerprints, subzy/baddns/nuclei detection, the 2024-2025 deleted-S3 → CI/CD supply-chain pivot, NS-delegation takeover.
  • references/cloud-saas-recon.md — cloud_enum multi-cloud, AADInternals/MicroBurst Azure tenant + blob recon (incl. the June-2025 Get-AADIntTenantDomains patch), GrayhatWarfare, GitHub/GitLab dorking with trufflehog/gitleaks/noseyparker.
  • references/breach-credential-intel.md — theHarvester 4.x, HIBP API v3 (ALIEN TXTBASE), DeHashed, infostealer-log intel (Snowflake-style aged creds), username/email format derivation, password-pattern modeling.
  • references/cve-exploit-intel.md — NVD 2.0 API + the 2026 selective-enrichment shift, EPSS v4, CISA KEV, Shodan InternetDB, searchsploit/nuclei, the KEV×EPSS×exposure prioritization stack.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Recon Osint AI skill do?

Use when mapping a target's external attack surface or gathering OSINT — subdomain enumeration, attack-surface mapping (httpx/katana/JS secrets), subdomain takeover, multi-cloud/Azure tenant recon, GitHub secret dorking, breach/infostealer credential intel, CVE prioritization (EPSS/KEV)

Why use Recon Osint on TypingMind?

Because you install it once and use it with any model. Recon Osint is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Recon Osint in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hypnguyen1209/offensive-claude/tree/main/skills/recon-osint. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Recon Osint?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Recon Osint?

As many as you like. As long as a model supports skills, you can use Recon Osint with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Recon Osint AI skill free?

Yes. It is published on GitHub by hypnguyen1209 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇