Works with the AI Agents you already use
valkyriescan network security auditor
Automated TCP port scanner and service banner auditor with CVE heuristic matching and Shodan integration.
Free
valkyriescan network security auditor
Example session with this skill installed
Run a security scan on my local staging server at 192.168.1.50 for ports 22, 80, and 443. I own this machine and authorize the scan.
- Read your context and instructions
- Compiled the valkyriescan network security
- Generated the document
I have performed the authorized TCP service audit on 192.168.1.50. The scan completed across 3 ports with service identification and external CVE enrichment enabled.
Network Security Audit Results
| Port | Service | Status | Banner / Identification | Heuristic Matches |
|---|---|---|---|---|
| 22 | SSH | OPEN | OpenSSH 8.2p1 Ubuntu 4ubuntu0.5 | CVE-2020-15778 (Potential) |
| 80 | HTTP | OPEN | Apache/2.4.41 (Ubuntu) | None |
| 443 | HTTPS | OPEN | Apache/2.4.41 (Ubuntu) | None |
External Intelligence (Shodan InternetDB)
- Resolved IP: 192.168.1.50
- Historical CVEs: CVE-2021-41773, CVE-2019-0211
- Note: These are historical records and may not reflect the current patch status of the target.
Files Generated
scan_result.json: Raw machine-readable scan data.scan_report.html: Formatted visual report for stakeholders.
Next steps
- Review the
scan_report.htmlfile in the project directory for detailed signature match descriptions. - Manually verify the OpenSSH version against vendor patch notes to confirm if CVE-2020-15778 is mitigated by backported fixes.
- Update the Apache service to the latest stable version to address historical CVEs found in the OSINT lookup.
scan_report.html
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Identifying vulnerabilities manually across network assets is slow and error-prone. This skill automates TCP service discovery and banner-based pattern matching to find potential security gaps without the overhead of heavy enterprise scanners.
What it does
- Service Discovery attempts TCP connections to specific port ranges to identify active listeners.
- Banner Grabbing extracts version strings from SSH, HTTP, and FTP services for identification.
- Signature Matching compares observed banners against a local JSON regex catalog for known vulnerability patterns.
- OSINT Enrichment queries Shodan InternetDB for historical CVE data linked to the target IP.
- Automated Reporting generates structured JSON and HTML files detailing open ports and heuristic matches.
How it works
- Target Validation resolves the hostname and verifies the user has authorization for the specific IP or domain.
- Scan Execution runs
valkyriescanwith defined port lists, thread counts, and timeout settings. - Intelligence Gathering processes local signatures and optional external Shodan lookups.
- Report Generation produces
scan_result.jsonandscan_report.htmlfor technical review.
Frameworks & tools
Built with Python 3.9 using the standard library for core scanning. Integrates with Shodan InternetDB API for external threat intelligence.
Why this beats prompting it yourself
Generic prompts often hallucinate network protocols or suggest dangerous exploitation commands. This skill enforces a strict "scan-only" workflow with built-in authorization gates and cautious reporting standards that separate observed facts from heuristic guesses.
Use cases
- Audit local dev environments for accidentally exposed management ports.
- Verify service version strings during a defensive hardening sprint.
- Perform quick, non-intrusive reconnaissance on authorized infrastructure.
Known limitations
Supports TCP only; no UDP scanning available. Banner matching is best-effort and requires manual verification against actual patch levels. External Shodan queries disclose the target IP.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
Supports TCP only; no UDP scanning. Banner matching produces heuristics, not proof of exploitability. External Shodan lookups disclose target IP to a third party.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
- Accounts
Shodan
- Software
Python
Git
Terminal / Shell: Required to execute the Python scanner and its tests. Read Files: Required to access the scanner modules and vulnerability signature database. Write Files: Required to generate JSON and HTML scan reports. Network Access: Required for authorized TCP port scanning and Shodan Inter
Permissions
Allowed Hosts