
External OSINT Reconnaissance
Maps an organization's public internet footprint using passive OSINT for authorized pentests
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Stars
- 35,430
- Licence
- Apache-2.0
- Files
- 3 files
What it does
Once installed, the agent follows a structured passive reconnaissance playbook against a target organization's domain: finding subdomains and DNS records, listing internet-facing services and cloud storage, gathering employee and email-format information, checking for leaked credentials and exposed documents, and profiling the technology stack. It explains which open-source tools and search techniques to use at each step and how to organize the findings into a target profile. A bundled Python script can also query certificate transparency logs, public DNS over HTTPS, and Shodan.
Great for
- Penetration testers preparing the passive information-gathering phase of an authorized engagement
- Red team operators scoping an organization's external attack surface before active testing
- Security students learning how external footprinting and OSINT are structured
Skip it if
- Investigating or monitoring private individuals, which the skill itself prohibits; it is risky and may breach privacy laws like GDPR or CCPA without a legitimate authorized scope
- Organizations without written authorization for reconnaissance, since collecting employee data and leaked credentials without permission can be illegal
- Non-security users wanting general company research, since the workflow is oriented to attack surface and social engineering preparation
Try asking
- “Map the external attack surface of example-corp.com for our authorized pentest, starting with subdomains and certificate transparency logs”
- “Build a list of likely employee email formats and key IT and security staff for an approved social engineering assessment”
- “Check public code repositories and breach databases for exposed credentials tied to our client's domain”
- “Profile the web technologies and TLS configuration exposed by the client's public websites”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 3 original files, the Apache-2.0 licence and an attribution note.
conducting-external-reconnaissance-with-osint.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip conducting-external-reconnaissance-with-osint.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip conducting-external-reconnaissance-with-osint.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Confirm written scope and authorization before running any query, and keep a record of what was collected and why
- Review scripts/agent.py before running it, since it sends queries to third-party services such as crt.sh, dns.google and Shodan using your API key
- Ask the agent to stay passive and avoid active scanning or zone transfer attempts unless the engagement explicitly allows them
What's inside
- references/api-reference.md
- scripts/agent.py
- SKILL.md
Redistributed unmodified from mukul975/Anthropic-Cybersecurity-Skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.