AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Opencrow Network Toolbox

skill-02loveslollipop-opencrow-opencrow-network-toolbox · by 02loveslollipop

Use the best available portable Python runtime and installed network tooling for packet- and protocol-level CTF tasks. Prefer a detected `ctf` environment. Use when an agent needs `scapy`, `tshark`, `tcpdump`, `nmap`, `nc`, or `socat` for packet work, capture analysis, or service triage.

↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-02loveslollipop-opencrow-opencrow-network-toolbox

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-02loveslollipop-opencrow-opencrow-network-toolbox)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● today

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Opencrow Network Toolbox? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

OpenCROW Network Toolbox

Runtime preflight

Probe required commands with command -v and Python modules with importlib.util.find_spec before use. Prefer a PATH-resolved OpenCROW MCP helper or the ctf/sage environment when available, then the managed helper or system Python. If a capability is missing, stop that path safely and report the exact missing command or module.

Use this skill for network artifact work that spans both Python packet tooling and native capture or triage tools: scapy, tshark, tcpdump, nmap, nc, and socat.

Quick Start

Start the MCP server from the installed CLI:

opencrow-network-mcp

Run inline Python in ctf:

python3 scripts/run_network_python.py --code 'from scapy.all import IP, TCP; print((IP(dst=\"127.0.0.1\")/TCP(dport=31337)).summary())'

Run a packet helper:

python3 scripts/run_network_python.py --file /absolute/path/to/packets.py

Verify the mapped stack:

python3 scripts/verify_toolkit.py

Workflow

  1. Start with the MCP server and call toolbox_info, toolbox_verify, and toolbox_capabilities.
  2. Use network_pcap_inspect first when you already have a capture or need a quick filtered look at traffic.
  3. Use network_scan to map reachable services before deeper protocol work.
  4. Use network_socket_probe for one-shot TCP or UDP validation without opening a persistent async session.
  5. Use network_python for Scapy-driven packet generation, decoding, or challenge-specific protocol logic.
  6. Use netcat-async or ssh-async separately when you need a long-lived interactive session rather than packet tooling.
  7. Read [references/tooling.md](references/tooling.md) for quick guidance.

Tool Selection

  • Use scapy for packet crafting, sniffing, protocol parsing, PCAP analysis, and challenge-specific dissectors.
  • Use opencrow-network-mcp first for typed MCP access to capture inspection, scanning, probing, and Scapy execution.
  • Use tshark for quick PCAP summaries, display filters, and protocol-aware decoding.
  • Use tcpdump for capture creation and fast packet inspection from the shell.
  • Use nmap for host, port, and service discovery before deeper protocol analysis.
  • Use nc or socat for quick socket experiments, port relays, or test servers.
  • Use plain Python socket code only when the task is simpler than full packet work.
  • Use netcat-async when the service is an interactive TCP stream and session persistence matters more than packet structure.

Resources

  • opencrow-network-mcp: stdio MCP server for typed PCAP inspection, scanning, socket probing, and Scapy execution.
  • scripts/run_network_python.py: execute inline code or a .py file inside the ctf environment.
  • scripts/verify_toolkit.py: confirm that scapy is available.
  • references/tooling.md: quick selection notes for network workflows.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills