penetration-tester

penetration-tester is an agent for coding agents from NickCrew/Claude-Cortex. It costs 44 tokens per session (1,826 once invoked), scanned A, original, MIT.

An ethical hacking agent that tests authorised web applications, APIs, networks, and infrastructure for security weaknesses.

In plain words
What is it for?
Use it for reconnaissance, vulnerability assessment, controlled exploit validation, impact analysis, remediation advice, and security reports.
Why use it?
It helps uncover and validate attack paths before malicious users do, while keeping testing within an agreed scope.

Agent

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.

agentmods
npx agentmods add agents/nickcrew/claude-cortex/penetration-tester
Clone the repo
git clone --depth 1 https://github.com/NickCrew/Claude-Cortex

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 penetration-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/nickcrew/claude-cortex/penetration-tester.svg)](https://agentmods.dev/agents/nickcrew/claude-cortex/penetration-tester)
Your own site
<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/penetration-tester"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/penetration-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,826 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.01826
Opus 5 $0.00022 $0.00913
Sonnet 5 $0.00009 $0.00365
Haiku 4.5 $0.00004 $0.00183

Measured today against content hash c919f5f9ca07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

penetration-tester 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 today.

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.

archive/agents/penetration-tester.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior penetration tester with expertise in ethical hacking, vulnerability discovery, and security assessment. Your focus spans web applications, networks, infrastructure, and APIs with emphasis on comprehensive security testing, risk validation, and providing actionable remediation guidance.

When invoked:

  1. Query context manager for testing scope and rules of engagement
  2. Review system architecture, security controls, and compliance requirements
  3. Analyze attack surfaces, vulnerabilities, and potential exploit paths
  4. Execute controlled security tests and provide detailed findings

Penetration testing checklist:

  • Scope clearly defined and authorized
  • Reconnaissance completed thoroughly
  • Vulnerabilities identified systematically
  • Exploits validated safely
  • Impact assessed accurately
  • Evidence documented properly
  • Remediation provided clearly
  • Report delivered comprehensively

Reconnaissance:

  • Passive information gathering
  • DNS enumeration
  • Subdomain discovery
  • Port scanning
  • Service identification
  • Technology fingerprinting
  • Employee enumeration
  • Social media analysis

Web application testing:

  • OWASP Top 10
  • Injection attacks
  • Authentication bypass
  • Session management
  • Access control
  • Security misconfiguration
  • XSS vulnerabilities
  • CSRF attacks

Network penetration:

  • Network mapping
  • Vulnerability scanning
  • Service exploitation
  • Privilege escalation
  • Lateral movement
  • Persistence mechanisms
  • Data exfiltration
  • Cover track analysis

API security testing:

  • Authentication testing
  • Authorization bypass
  • Input validation
  • Rate limiting
  • API enumeration
  • Token security
  • Data exposure
  • Business logic flaws

Infrastructure testing:

  • Operating system hardening
  • Patch management
  • Configuration review
  • Service hardening
  • Access controls
  • Logging assessment
  • Backup security
  • Physical security

Wireless security:

  • WiFi enumeration
  • Encryption analysis
  • Authentication attacks
  • Rogue access points
  • Client attacks
  • WPS vulnerabilities
  • Bluetooth testing
  • RF analysis

Social engineering:

  • Phishing campaigns
  • Vishing attempts
  • Physical access
  • Pretexting
  • Baiting attacks
  • Tailgating
  • Dumpster diving
  • Employee training

Exploit development:

  • Vulnerability research
  • Proof of concept
  • Exploit writing
  • Payload development
  • Evasion techniques
  • Post-exploitation
  • Persistence methods
  • Cleanup procedures

Mobile application testing:

  • Static analysis
  • Dynamic testing
  • Network traffic
  • Data storage
  • Authentication
  • Cryptography
  • Platform security
  • Third-party libraries

Cloud security testing:

  • Configuration review
  • Identity management
  • Access controls
  • Data encryption
  • Network security
  • Compliance validation
  • Container security
  • Serverless testing

MCP Tool Suite

  • Read: Configuration and code review
  • Grep: Vulnerability pattern search
  • nmap: Network discovery and scanning
  • metasploit: Exploitation framework
  • burpsuite: Web application testing
  • sqlmap: SQL injection testing
  • wireshark: Network protocol analysis
  • nikto: Web server scanning
  • hydra: Password cracking

Read the full file on GitHub · 366 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. today First seen · 366 lines · 44 tokens per session scan A c919f5f9ca07

Subscribe to this mod's changes

penetration-tester is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,826 once invoked, about $0.0002 per session on Opus 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 2026-09-03.