osint-recon
Skill489 starsChanged 5 days agoMITView on GitHub
Gather and correlate open source intelligence from public sources for authorized investigations, threat intelligence, and attack surface assessment. Use when the user mentions 'OSINT,' 'open source intelligence,' 'digital footprint,' 'public records,' 'threat intelligence,' 'investigate a domain,' or needs to research a target using publicly available data.
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Run these to map a target's infrastructure:
- Distinctive: line 111
Only use publicly available sources
- Distinctive: line 112
Never attempt to access private or authenticated systems
- Distinctive: line 113
Do not aggregate PII beyond what is necessary for the stated objective
- Distinctive: line 116
If a finding could cause harm if misused, note the sensitivity
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OSINT Recon — Open Source Intelligence Gathering
Systematically gather, analyze, and correlate publicly available information from open sources.
Cross-references: recon for the active/passive target-mapping pass against an authorized system (DNS, ports, fingerprinting) — osint-recon focuses on people, organizations, leaked data, and historical artifacts; the two pair naturally. breach-patterns for ingesting public breach intelligence into your own preemptive assessments. incident-triage if OSINT surfaces evidence the user is already compromised.
Authorization and Ethics Check
Before proceeding, confirm:
- The investigation has a legitimate purpose (threat intel, authorized assessment, CTF, defensive research)
- For an assessment of an organization, the organization (or the client that engaged you) has authorized it in writing
- You are only gathering publicly available information
- Results will not be used for harassment, stalking, or doxing
Refuse requests that target individuals for harassment or aggregate private information beyond what the objective requires.
Collection Techniques
Domain and Infrastructure OSINT
Run these to map a target's infrastructure:
whois <domain> # Registration data
dig any <domain> # DNS recordsQuery certificate transparency for subdomains:
curl -s "https://crt.sh/?q=%25.<domain>&output=json" | jq -r '.[].name_value' | sort -uAdditional sources: SecurityTrails, DNSDumpster, ipinfo.io, bgp.he.net, Wayback Machine, Shodan, Censys.
Organization OSINT
- Company registrations, filings, SEC records (public companies)
- LinkedIn company page — employee count, roles, tech stack hints
- Job postings — reveal internal tools, tech stack, pain points
- Press releases and news articles
- GitHub/GitLab organization pages and public repositories
- Patent filings
Email and Username OSINT
- Email format patterns (e.g., first.last@domain.com)
- HaveIBeenPwned — check for breach exposure (check only, never distribute breach data)
- PGP key servers for email discovery
- Gravatar lookups for email-to-identity correlation
Document and File OSINT
- Extract metadata from public documents:
exiftool <file>reveals author, software, GPS, timestamps - Google dorking:
site:<domain> filetype:pdf,site:<domain> filetype:xlsx - Pastebin and code paste site monitoring
- Public cloud storage enumeration (S3 buckets, GCS buckets with predictable names)
Threat Intelligence
- CVE databases for the target's technology stack
- Exploit databases (exploit-db, searchsploit)
- Threat feeds and IOC databases (VirusTotal, MalwareBazaar, OTX)
- Abuse contact databases
Analysis
- Cross-reference findings across multiple sources
- Validate information with at least two independent sources
- Build a timeline of events when investigating incidents
- Map relationships between entities (people, domains, IPs, organizations)
- Rate confidence: High (multiple corroborating sources), Medium (single reliable source), Low (unverified)
Output Format
# OSINT Report
## Objective: [what we're investigating and why]
## Target: [entity/domain/person]
## Date: [date]
### Collection Summary
| Source | Findings | Confidence |
|--------|----------|------------|
### Key Findings
#### Finding 1: [Title]
- **Source:** [where this was found]
- **Details:** [what was discovered]
- **Confidence:** High / Medium / Low
- **Relevance:** [why this matters to the objective]
### Correlations
[How different findings connect to each other]
### Intelligence Gaps
[What we couldn't find or verify]
### Recommendations
[Next steps and actionable intelligence]Boundaries
- Only use publicly available sources
- Never attempt to access private or authenticated systems
- Do not aggregate PII beyond what is necessary for the stated objective
- Attribute all findings to their source
- Rate confidence levels honestly — do not overstate certainty
- If a finding could cause harm if misused, note the sensitivity
- Refuse requests for doxing, stalking, or unauthorized surveillance
References
- OSINT Framework (osintframework.com)
- SANS OSINT resource list
- Bellingcat Online Investigation Toolkit
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- imMamdouhaboammar/cybersecurity-skills★ 096% same
Wrote their own version · 2
- Cat-tj/osint-recon★ 0same name
- TheWatcher01/skills★ 0same name
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.
In this repository42 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-supply-chain-auditSkill
- ai-risk-managementSkill
- api-auditSkill
- breach-patternsSkill
- business-logic-testingSkill
- cicd-securitySkill
- cloud-auditSkill
- container-auditSkill
- control-auditSkill
- crypto-auditSkill
- csf-mappingSkill
- dependency-auditSkill
- disk-forensicsSkill
- finding-triageSkill
- fuzzing-harnessSkill
- hipaa-auditSkill
- iam-auditSkill
- incident-triageSkill
- log-watchSkill
- malware-triageSkill
- mobile-auditSkill
- native-code-reviewSkill
- owasp-auditSkill
- patch-sweepSkill
- pci-auditSkill
- personal-opsecSkill
- privacy-engineeringSkill
- prompt-injectionSkill
- reconSkill
- red-team-engagementSkill
- scanner-pipelineSkill
- secrets-auditSkill
- security-commsSkill
- security-startSkill
- siem-detectionSkill
- soc-operationsSkill
- threat-huntingSkill
- threat-modelingSkill
- variant-analysisSkill
- vuln-researchSkill
- web-pentestSkill
Does 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.

