osint
Skill12 starsChanged 9 months agoMITView on GitHub
Solve CTF OSINT (open source intelligence) challenges: username enumeration, domain recon, social media investigation, geolocation from images, and public records research. Use when given a username, email, domain, or photo to investigate. Triggers: "find this person", "username lookup", "who is", "geolocation", "reverse image search", "EXIF GPS", "whois", "domain recon", "social media". Tools: sherlock, theHarvester, exiftool, whois, dig. NOT for web app exploitation (use web).
18 other projects use a version of this.
Adopted by
Most recently taken up by
- OpenOSINT/OpenOSINTtheir own version, first seen Nov 8, 2026
- genericService/claude-skillstheir own version, first seen Nov 8, 2026
- mahumadad/quarrytheir own version, first seen Nov 8, 2026
- madeinoz67/madeinoz-osint-skilltheir own version, first seen Nov 1, 2026
- assafkip/huntkittheir own version, first seen Nov 1, 2026
- assafkip/investigators-copilottheir own version, first seen Oct 25, 2026
Used with
Projects with it also use sqli, xss and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SubhiSecSkillsqli
Hunt SQL injection in REST/GraphQL/SOAP/raw parameters using sqlmap, ghauri, manual UNION/Time/Boolean techniques, and custom WAF-bypass tamper scripts. Use when an input flows into a database query or when the user has identified a parameter that might be vulnerable.
Also in 3 projects that use this
SubhiSecSkillxss
Hunt reflected, stored, and DOM-based Cross-Site Scripting (XSS) including CSP bypass, polyglot payloads, mutation XSS (mXSS), markdown XSS, and template XSS. Use when the user has identified a parameter or input that reflects to the page, or wants to test for XSS in a specific input.
Also in 3 projects that use this
jord0-cmdSkillRECON
Deep technical research that persists. Use when: exploring new technologies, investigating frameworks, comparative analysis of tools, understanding complex systems, or any research task that should be saved for future reference. Invokes Claude's built-in research agent and auto-saves results to a knowledge base for retrieval across sessions.
Also in 4 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- OpenOSINT/OpenOSINT★ 1.9ksame name
- smixs/osint-skill★ 119same name
- assafkip/huntkit★ 74same name
- assafkip/investigators-copilot★ 74same name
- buriedsignals/spotlight★ 59same name
- CarbeneAI/Forge★ 9same name
- madeinoz67/madeinoz-osint-skill★ 8same name
- sunilgentyala/OmniRed★ 5same name
- kekurttel/pentest-skills★ 4same name
- Kur1sulab/blackbox★ 3same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Use this command for challenges involving:
- Very specific: line 85
When using /ctf-kit:team-solve with an OSINT challenge, the lead spawns 3 specialists.
- Distinctive: line 87
All OSINT teammates require plan approval: before querying external services.
- Distinctive: line 104
Before any teammate queries an external service:
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CTF OSINT
Gather open source intelligence for OSINT challenges.
When to Use
Use this command for challenges involving:
- Username searching
- Domain reconnaissance
- Social media investigation
- Geolocation from images
- Public records research
Bundled Scripts
- check-tools.sh — Verify required OSINT tools are installed
- run-sherlock.sh — Username enumeration across platforms. Outputs JSON with found profiles categorized by type (social media, code platforms, other).
- run-exiftool.sh — OSINT-focused metadata extraction with GPS coordinate extraction. Outputs JSON with interesting fields, GPS data, and flag detection.
Instructions
- First check tool availability:
bash scripts/check-tools.sh For username enumeration (outputs structured JSON):
bash scripts/run-sherlock.sh <username>JSON output includes:
profiles[]: all found profiles with site and URLsocial_media[]: social media profiles specificallycode_platforms[]: GitHub, GitLab, etc.suggestions: cross-referencing guidance
For image geolocation (outputs structured JSON):
bash scripts/run-exiftool.sh <image>JSON output includes:
gps_data: GPS coordinates if presentinteresting_fields[]: CTF-relevant metadata (comments, author, etc.)has_flag: true if flag pattern found in metadata
For domain reconnaissance:
theHarvester -d target.com -b all dig target.com ANY whois target.com- Online resources:
- Maps: Google Maps, Google Earth
- Archive: web.archive.org
- Reverse Image: Google Images, TinEye
- Social: LinkedIn, Twitter, Facebook
- Breach Data: haveibeenpwned.com
OSINT Workflow
run-sherlock.sh username→ check JSON for profiles- Cross-reference social and code platforms
run-exiftool.sh image.jpg→ check JSON for GPS, metadata clues- Build complete picture from combined findings
Team Roles
When using /ctf-kit:team-solve with an OSINT challenge, the lead spawns 3 specialists.
All OSINT teammates require plan approval before querying external services.
| Role | Teammate Name | Focus | Tools | First Action |
| People & Social | social-investigator | Username enumeration, social media profiling, identity correlation, breach data | sherlock, scripts/run-sherlock.sh | Run sherlock on any usernames, cross-reference profiles across platforms |
| Domain & Infrastructure | domain-analyst | WHOIS, DNS records, subdomain enumeration, email harvesting, IP geolocation, certificate transparency | whois, dig, theHarvester | Run whois + dig on domains, check certificate transparency logs |
| Geolocation & Media | geo-analyst | EXIF GPS extraction, reverse image search, visual landmark identification, Street View correlation | exiftool, scripts/run-exiftool.sh | Extract EXIF GPS, identify visual landmarks, cross-reference with maps |
When to broadcast
- Social: "Username 'target123' has GitHub with a repo containing coordinates" — geo analyst investigates
- Domain: "Domain registered to email X, also found on social platform Y" — social investigator digs deeper
- Geo: "EXIF GPS points to 48.8584, 2.2945 (Eiffel Tower)" — others search for related context
- Any: "Found the flag" — immediate broadcast, all stop
Plan approval flow
Before any teammate queries an external service:
- Teammate describes the query and target
- Lead reviews for scope (only target what the challenge asks for)
- Lead approves or suggests alternative approach
Example Usage
/ctf-kit:osint image.jpg
/ctf-kit:osint challenge.txtDoes 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.

