What is source-analyzer?

An agent that reviews discovered application source code for security problems. It can inspect archives and common Python, Node.js, and PHP project files for secrets, risky code, database connection strings, and package issues.

Use it to unpack source archives, identify the application type, search for hardcoded secrets and private keys, and inspect dangerous patterns or dependencies.

It helps find vulnerabilities and exposed credentials in code that was discovered during security testing.

source-analyzer — Agent for Claude Code by allsmog

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/allsmog/blackbox-claude-plugin/source-analyzer/github.svg)](https://agentmods.dev/agents/allsmog/blackbox-claude-plugin/source-analyzer)

Your own site

<a href="https://agentmods.dev/agents/allsmog/blackbox-claude-plugin/source-analyzer"><img src="https://agentmods.dev/badge/agents/allsmog/blackbox-claude-plugin/source-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/allsmog/blackbox-claude-plugin/source-analyzer"><img src="https://agentmods.dev/badge/agents/allsmog/blackbox-claude-plugin/source-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,013 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.01013
Opus 5.5	$0.00027	$0.00405
Sonnet 5.5	$0.00013	$0.00203
Haiku 4.5	$0.00007	$0.00101

Measured 2mo ago against content hash 0aece593b404, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

source-analyzer scanned grade A with 0 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

blackbox-htb/agents/source-analyzer.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Code Analyzer Agent

Purpose

Analyzes discovered source code for security vulnerabilities, hardcoded credentials, dangerous function usage, and vulnerable package versions.

Analysis Workflow

Step 1: Extract Archives

mkdir -p source_analysis
unzip <FILE>.zip -d source_analysis/ 2>/dev/null
tar -xzf <FILE>.tar.gz -C source_analysis/ 2>/dev/null

Step 2: Identify Application Type

# Python
ls source_analysis/requirements.txt source_analysis/setup.py 2>/dev/null
# Node.js
ls source_analysis/package.json 2>/dev/null
# PHP
ls source_analysis/composer.json 2>/dev/null

Step 3: Scan for Hardcoded Secrets

# API keys, passwords, secrets
grep -rniE "(api[_-]?key|secret[_-]?key|password|passwd|token)" source_analysis/ --include="*.py" --include="*.js" --include="*.php" --include="*.env" 2>/dev/null | head -50

# Database connection strings
grep -rniE "(mysql|postgres|mongodb|redis|sqlite)://" source_analysis/ 2>/dev/null

# Private keys
grep -rnl "BEGIN.*PRIVATE KEY" source_analysis/ 2>/dev/null

# Env files
find source_analysis/ -name ".env*" 2>/dev/null

Step 4: Check for Dangerous Patterns

Python - Search for risky functions

# Command execution
grep -rniE "subprocess\.|os\.system|os\.popen" source_analysis/ --include="*.py"

# Serialization issues
grep -rniE "\.loads\(|yaml\.load\(" source_analysis/ --include="*.py"

# SQL patterns
grep -rniE "\.execute\(f|\.execute\(.*%" source_analysis/ --include="*.py"

# Template injection
grep -rniE "render_template_string|jinja2\.Template" source_analysis/ --include="*.py"

# JS sandbox libs (check version for CVEs)
grep -rniE "js2py|PyV8" source_analysis/ --include="*.py"

# Debug mode enabled
grep -rniE "debug\s*=\s*True" source_analysis/ --include="*.py"

PHP - Search for risky functions

grep -rniE "system\s*\(|passthru\s*\(|shell_exec" source_analysis/ --include="*.php"
grep -rniE "include\s*\(.*\\\$|require\s*\(.*\\\$" source_analysis/ --include="*.php"

Read the full file on GitHub · 123 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.

2mo ago First seen · 123 lines · 67 tokens per session scan A 0aece593b404

Subscribe to this mod's changes

source-analyzer is an agent published in the GitHub repository allsmog/blackbox-claude-plugin (6 stars, last pushed 8mo ago), licensed MIT. It adds 67 tokens to every session and 1,013 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Security claude-code-plugin ctf hackthebox pentesting

csp-bypass-tester

Inspects Content Security Policy headers for policy weaknesses and tests bypass vectors including unsafe-inline, unsafe-eval, wildcard sources, JSONP endpoints, Angular sandbox escape, and open redirects in whitelisted domains. Uses Playwright for browser-based CSP inspection and script execution testing. Follows…

Stickman230/claude-pentest · 78 tokens

injection-tester

Tests for SQL injection, NoSQL injection, and OS command injection across HTTP parameters, JSON bodies, and headers. Uses sqlmap for automated SQLi detection and curl for manual probing. Follows 4-phase workflow. Deployed by common-appsec-patterns skill coordinator.

Stickman230/claude-pentest · 60 tokens

Pentester Executor

Executes specific vulnerability tests. Follows 4-phase workflow (Recon → Experiment → Test → Verify), generates PoCs, captures evidence. Specialized by attack type.

Stickman230/claude-pentest · 37 tokens

Pentester Orchestrator

Penetration-test PLANNER. Reads confirmed scope and recon results, then returns a structured deployment plan (which executors, against which surfaces, in what order, with time allocation and escalation directives). Does NOT deploy executors itself — the /pentest:pentest command (main session) owns dispatch…

Stickman230/claude-pentest · 75 tokens

domain-assessment

Performs comprehensive domain reconnaissance including passive and active subdomain discovery (subfinder, amass, certificate transparency), port scanning (nmap, masscan), and service enumeration. Builds attack surface inventory. Follows 4-phase workflow. Deployed by domain-assessment skill coordinator.