pentest-recon
Skill8 starsChanged 3 months agoMITView on GitHub
Reconnaissance and enumeration advisory — Nmap/Nessus/Nikto/BloodHound output parsing, attack surface prioritization, next-step suggestions. Includes OSINT (domain recon, email harvest, breach data). Triggers on recon, reconnaissance, enumeration, Nmap output, attack surface, target prioritization, subdomain enum, port scan analysis, OSINT, domain recon.
In this repository63 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-automationSkill
- consultingSkill
- contentSkill
- customer-successSkill
- data-analyticsSkill
- designSkill
- design-tokensSkill
- developmentSkill
- devopsSkill
- ecommerceSkill
- emailSkill
- expo-app-configSkill
- expo-config-pluginSkill
- expo-dev-clientSkill
- expo-eas-buildSkill
- expo-eas-submitSkill
- expo-eas-updateSkill
- expo-modulesSkill
- expo-notificationsSkill
- expo-orchestratorSkill
- expo-prebuildSkill
- expo-routerSkill
- expo-troubleshootingSkill
- financeSkill
- frontend-tasteSkill
- marketingSkill
- market-researchSkill
- mobileSkill
- pentest-adSkill
- pentest-apiSkill
- pentest-bizlogicSkill
- pentest-bugbountySkill
- pentest-cicdSkill
- pentest-cloudSkill
- pentest-credentialsSkill
- pentest-ctfSkill
- pentest-detectionSkill
- pentest-engagementSkill
- pentest-exploit-chainSkill
- pentest-forensicsSkill
- pentest-llmSkill
- pentest-malwareSkill
- pentest-mobileSkill
- pentest-opsec-evidenceSkill
- pentest-orchestratorSkill
- pentest-privescSkill
- pentest-reportSkill
- pentest-socialSkill
- pentest-stigSkill
- pentest-threat-modelSkill
- pentest-webSkill
- pentest-wirelessSkill
- productivitySkill
- productSkill
- salesSkill
- security-checkSkill
- securitySkill
- seo-crawl-budgetSkill
- seoSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 69
If the user grants scope approval, the skill can suggest the following commands (with examples):
- Very specific: line 85
Every command is explained first, then run via the Bash tool (on user approval).
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
pentest-recon
Recon output analysis + attack-surface prioritization + next-step suggestions. Advisory mode — the user pastes output, the skill analyzes it. Active command composing requires a scope declaration.
Triggers
- "nmap output" / "review the scan result"
- "Nessus report"
- "I ran a subdomain enum"
- "where is the attack surface"
- "which target is the priority"
- "BloodHound graph analysis"
- "let's do OSINT"
Input Types
| Input | Skill Behavior |
| Nmap XML/text output | Port + service + version + script output parse, CVE lookup suggestion |
| Nessus / OpenVAS report | Severity + CVSS prioritize, critical findings list |
| Nikto output | Web vulnerability filtering, false positives weeded out |
| BloodHound JSON | Find high-value target paths, attack path prioritization |
| Masscan/Naabu output | Open-port list -> service enum suggestion |
| WHOIS / certificate transparency | Subdomain expansion, additional domain discovery |
Output Template
## Recon Analysis — <target>
### Detection
- 3 open ports: 22/SSH, 80/HTTP, 443/HTTPS
- HTTP: nginx 1.18.0 (CVE-2021-23017)
- HTTPS: Self-signed cert, expired 2024-03-15
- SSH: OpenSSH 7.6p1 (CVE-2018-15473)
### Prioritization
1. [HIGH] CVE-2021-23017 — nginx DNS resolver — exploitable, public PoC available
2. [MEDIUM] OpenSSH user enum (CVE-2018-15473) — username discovery
3. [LOW] Cert expired — config issue, no exploitation value
### Next Step (suggested)
- Active: `nikto -h <target>` (MODERATE OPSEC)
- Passive: SecurityTrails / Censys additional subdomains (QUIET)
- Targeted: nginx version-specific exploit-db search
### Skipped Areas
- UDP scan not done (53, 161 standard practice)
- Vhost discovery skippedActive Command Composing (Scope Required)
If the user grants scope approval, the skill can suggest the following commands (with examples):
# QUIET — passive subdomain enum
subfinder -d example.com -silent
# MODERATE — TCP service scan, rate-limited
nmap -sT -sV --top-ports 1000 --max-rate 100 -oA scan_example_$(date +%Y%m%d_%H%M%S) <target>
# MODERATE — HTTP fingerprint
httpx -l hosts.txt -title -tech-detect -status-code -o httpx-results.txt
# QUIET — Cert transparency
curl for crt.sh: 'https://crt.sh/?q=%25.example.com&output=json'Every command is explained first, then run via the Bash tool (on user approval). An evidence file is created.
OSINT (passive collection)
| Source | Data | OPSEC |
| crt.sh | Subdomain (cert transparency) | QUIET |
| Shodan API | Open ports + banners | QUIET (authorized API) |
| Censys | TLS cert + port | QUIET |
| haveibeenpwned API | Email breach hit | QUIET |
| theHarvester | Email + employee | QUIET-MODERATE |
| LinkedIn (manual) | Employee role + dept | QUIET |
| GitHub search | Code leak, secret exposure | QUIET |
| Wayback Machine | Old endpoint, deprecated path | QUIET |
Prioritization Logic
| Factor | Weight |
| Public exploit availability (Exploit-DB, PoC repo) | x3 |
| CVSS >= 9.0 | x3 |
| Unauthenticated remote | x2 |
| Internet-facing | x2 |
| Likely default credential | x2 |
| Known RCE service (Tomcat manager, Jenkins, Confluence) | x3 |
Sort by score -> focus on the top 5 targets.
Out-of-Scope
- Running live exploits (see domain-specific skills like pentest-web, pentest-ad)
- Authoritative DNS zone transfer against external targets (DoS risk)
- Mass scan public internet
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.

