Skip to main content
skill CX Codex

osint — Claude Code skill: repository and secret reconnaissance

osint — a skill for passive intelligence gathering across code repositories, developer accounts, and exposed secrets. Discovers company repositories, scans commit history for sensitive data, maps API endpoints and internal infrastructure.

MIT 251 installs ★ 632 updated 2026-07-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add transilienceai/communitytools --skill osint -a claude-code
Open on GitHub

What osint does

osint operates in four phases: it enumerates GitHub, GitLab, and Bitbucket organizations for the target company, discovers employee personal accounts, then analyzes every repository found to map tech stack, languages, and dependencies. It scans current code and full commit history with gitleaks and trufflehog to catch secrets removed in past commits. Finally, it extracts API endpoints, authentication patterns, internal service names, and examines Dockerfiles and CI configs for infrastructure details.

The skill starts passive—searching through public APIs and pages—before cloning anything. Every discovered credential is recorded as a finding. Results are saved to data/reconnaissance/ and reports/ following the project's directory structure: a repository inventory, a reconnaissance report, and raw tool outputs.

It requires internet access to public registries and uses the gh CLI. Useful for security audits of your own codebase, threat assessment before a security incident, and code inventory before migration or compliance review.

What it helps with

  • enumerate all repositories across GitHub, GitLab, and Bitbucket for a company
  • scan full commit history for accidentally committed secrets and API keys
  • extract internal hostnames, IP addresses, and service endpoints from code
  • identify dependency versions with known vulnerabilities
  • discover personal developer accounts linked to the organization

Example prompts for the agent

  • Run osint reconnaissance on acmecorp across all platforms
  • Scan the full repository history of acmecorp for exposed credentials
  • Extract all internal endpoints and service names from acmecorp's codebase

How to install osint

1Skills CLI (Vercel)

npx skills add transilienceai/communitytools --skill osint -a claude-code

2Manually: put the files in place

~/.claude/skills/osint/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/osint/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about osint

How do I install osint for Claude Code?

Run npx skills add transilienceai/communitytools --skill osint -a claude-code in your terminal, then open ~/.claude/skills/osint/SKILL.md.

What does osint do?

The skill discovers and analyzes a company's code presence: it lists repositories, scans code for exposed secrets (keys, passwords, tokens) in current and historical commits, extracts internal addresses and service names, and identifies dependency vulnerabilities.

What tools and credentials does osint need?

Internet access to GitHub, GitLab, and Bitbucket. The skill includes or requires gitleaks, trufflehog, gitrob, and the gh CLI in your PATH.

Source text

SKILL.md · MIT
---
name: osint
description: Open-source intelligence gathering - company repository enumeration, secret scanning, git history analysis, employee footprint, and code exposure discovery.
---

# OSINT

Passive and semi-passive intelligence gathering focused on code repositories, developer footprints, and exposed secrets across public platforms.

## Phases

### 1. Organization Discovery
- Enumerate GitHub/GitLab/Bitbucket orgs for target company name variants
- Find employee personal accounts linked to the target org
- Identify archived, forked, and deleted repositories

### 2. Repository Analysis
- Map all repos: tech stack, languages, CI/CD, dependencies
- Identify internal hostnames, IPs, endpoints, environment names
- Check for `.env`, config files, secrets in current code

### 3. Secret & Credential Scanning
- Scan current code with `gitleaks` / `trufflehog`
- Scan full git history (secrets removed in commits are still accessible)
- Search with targeted dorks (see `reference/repository-recon.md`)

### 4. Code Intelligence
- Extract API endpoints, auth patterns, internal service names
- Review Dockerfiles, CI configs, IaC for infra details
- Check dependency files for version-specific CVE candidates

## Output

```
data/reconnaissance/repositories.json   # Repo inventory + findings
reports/reconnaissance_report.md        # OSINT section appended
raw/osint/                              # Raw tool outputs
```

## Tools

`trufflehog`, `gitleaks`, `gitrob`, GitHub/GitLab search, `gh` CLI, `git log`

## Rules

1. Passive discovery first (search APIs, public pages) before any cloning
2. Scan git history — deleted secrets are still in commit objects
3. Check employee personal accounts, not just org accounts
4. Document every discovered credential/secret immediately as a finding
5. All output saved to `{OUTPUT_DIR}/` per CLAUDE.md directory structure

## Reference

- `reference/repository-recon.md` - Dorks, tool commands, secret patterns, workflow

© transilienceai · MIT · transilienceai/communitytools

Similar skills

All skills for Security →

From the same set42

The whole set →
attack-path-stitcher attack-path-stitcher stitches isolated single-asset vulnerabilities into multi-hop attack paths across the infrastructure. Useful for uncovering breach routes to critical systems. CX Codex +1 1,500installs blockchain-security blockchain-security is a skill that checks Solidity contracts and blockchain CTF challenges for common EVM flaws, including storage, delegatecall, and access-control issues. CX Codex +1 875installs hackerone Parses HackerOne scope tables, runs parallel pentesting agents per asset, and formats verified reports after checking exploit PoCs. CX Codex +1 348installs reconnaissance Runs domain reconnaissance: subdomains, open ports, endpoints and APIs, then sorts the attack surface by risk. CX Codex +1 248installs cve-poc-generator The cve-poc-generator skill researches a CVE, writes a safe Python PoC, and produces a vulnerability report. Use it when you need sourced verification and remediation details. CX Codex +1 236installs social-engineering social-engineering is a Claude Code skill for planning authorized tests of human-factor security. It covers phishing, pretexting, voice-based attacks, and physical security checks. CX Codex +1 224installs api-security api-security is a Claude Code skill that tests REST, GraphQL, WebSocket, and Web-LLM interfaces for authorization flaws and injection bugs across large endpoint collections. CX Codex +1 220installs web-app-logic web-app-logic — a skill for finding vulnerabilities in web application logic that automated scanners miss: workflow bypass, race conditions, access control flaws, cache poisoning, and information disclosure. CX Codex +1 219installs

Project sponsors

Companies that keep this analytics open