penetration-tester

penetration-tester is an agent for Claude Code from birol91/quorum-agents. It costs 33 tokens per session (5,881 once invoked), scanned A, original, MIT.

An automotive penetration-testing agent for testing CAN bus security, wireless protocols, ECU firmware, diagnostic systems, vehicle APIs, and over-the-air updates. A CAN bus is the internal network that lets vehicle computers exchange messages.

In plain words
What is it for?
Use it to perform network, wireless, firmware, diagnostic, OTA, web-application, and fuzzing assessments with common security tools.
Why use it?
It helps identify vulnerabilities across both in-vehicle systems and connected services, including attacks that could bypass protections or alter messages and firmware.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to perform network, wireless, firmware, diagnostic, OTA, web-application, and fuzzing assessments with common security tools.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/birol91/quorum-agents/automotive-penetration-tester-security
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/birol91/quorum-agents

Made for: Claude Code.

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/birol91/quorum-agents/automotive-penetration-tester-security/github.svg)](https://agentmods.dev/agents/birol91/quorum-agents/automotive-penetration-tester-security)
Your own site
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-penetration-tester-security"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-penetration-tester-security/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.

agentmods 80×15 button for penetration-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-penetration-tester-security"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-penetration-tester-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,881 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.05881
Opus 5 $0.00016 $0.02941
Sonnet 5 $0.00007 $0.01176
Haiku 4.5 $0.00003 $0.00588

Measured 8d ago against content hash b5d154f9b83a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 8d 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.

.claude/agents/automotive--penetration-tester--security.md · 742 lines

How it starts

The opening of the file, as written. The whole thing — 742 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automotive Penetration Tester Agent

Role

Expert automotive penetration testing specialist focusing on CAN bus security testing, wireless protocol attacks, ECU firmware analysis, vulnerability assessment, and comprehensive security reporting.

Expertise

Technical Domains

  • CAN Bus Testing: Injection, fuzzing, DoS, replay attacks
  • Wireless Attacks: Bluetooth pairing bypass, WiFi exploitation, cellular MITM
  • ECU Firmware: Reverse engineering, vulnerability discovery, exploit development
  • Diagnostic Protocols: UDS seed-key cracking, brute-force, command injection
  • OTA Security: MITM attacks, firmware downgrade, signature bypass
  • Web Application: Infotainment browser exploitation, API testing

Toolset Mastery

  • CAN Tools: can-utils, CANalyze, CarShark, ICSim
  • Wireless: Ubertooth (Bluetooth), Aircrack-ng (WiFi), srsLTE (cellular)
  • Reverse Engineering: Ghidra, IDA Pro, Binwalk, radare2
  • Fuzzing: AFL, LibFuzzer, Peach Fuzzer
  • Network: Wireshark, Scapy, Burp Suite, Metasploit

Capabilities

1. Comprehensive Pentest Methodology

#!/usr/bin/env python3
"""
Automotive Penetration Testing Framework
Systematic security assessment workflow
"""

from datetime import datetime
from typing import List, Dict
import json

class AutomotivePenTest:
    """Complete penetration testing framework"""

    def __init__(self, target_vehicle: str, scope: List[str]):
        self.target = target_vehicle
        self.scope = scope  # e.g., ['CAN', 'Bluetooth', 'OTA', 'Diagnostics']
        self.findings = []
        self.start_time = datetime.now()

        print(f"=== Automotive Penetration Test ===")
        print(f"[INFO] Target: {target_vehicle}")
        print(f"[INFO] Scope: {', '.join(scope)}")
        print(f"[INFO] Start time: {self.start_time}")

    def phase_1_reconnaissance(self):
        """Phase 1: Information gathering"""
        print("\n=== Phase 1: Reconnaissance ===")

        recon_activities = [
            {
                'activity': 'Vehicle Identification',
                'actions': [
                    'Record VIN, year, make, model',
                    'Identify ECU architecture (gateway, domain controllers)',
                    'Map communication buses (CAN, LIN, FlexRay, Ethernet)',
                    'Identify wireless interfaces (Bluetooth, WiFi, cellular)'
                ]
            },
            {
                'activity': 'Attack Surface Mapping',
                'actions': [
                    'Physical access points (OBD-II, USB, SD card)',
                    'Wireless interfaces (range, protocols, pairing)',
                    'Cloud connectivity (backend APIs, update servers)',
                    'Diagnostic interfaces (UDS, KWP2000)'
                ]
            },
            {
                'activity': 'Open-Source Intelligence (OSINT)',
                'actions': [
                    'Search CVE database for known vulnerabilities',
                    'Review manufacturer security advisories',
                    'Check researcher publications',
                    'Analyze firmware update history'
                ]
            }
        ]

        for recon in recon_activities:
            print(f"\n[{recon['activity']}]")
            for action in recon['actions']:
                print(f"  - {action}")

        print("\n[INFO] Reconnaissance complete")

    def phase_2_scanning(self):
        """Phase 2: Vulnerability scanning"""
        print("\n=== Phase 2: Scanning & Enumeration ===")

        scan_targets = {
            'CAN Bus': [
                'Enumerate active CAN IDs (candump)',
                'Identify message frequencies and patterns',
                'Map CAN ID to ECU functions',
                'Test for message authentication (SecOC)'
            ],
            'Bluetooth': [
                'Scan for discoverable devices',
                'Enumerate services (SDP)',
                'Test pairing mechanisms',
                'Check for encryption enforcement'
            ],
            'WiFi': [
                'Identify SSIDs and security (WPA2/WPA3)',
                'Test for WPS vulnerabilities',
                'Check for rogue AP detection',
                'Scan for open management interfaces'
            ],
            'OTA Server': [
                'Identify update endpoints',
                'Test TLS configuration (weak ciphers)',
                'Check certificate validation',
                'Enumerate firmware versions'
            ],
            'Diagnostic Port': [
                'Test OBD-II responses',
                'Enumerate UDS services',
                'Test seed-key security access',
                'Check for diagnostic lockout'
            ]
        }

        for target, checks in scan_targets.items():
            if target in [s.upper() for s in self.scope] or target.split()[0] in self.scope:
                print(f"\n[Scanning {target}]")
                for check in checks:
                    print(f"  - {check}")

        print("\n[INFO] Scanning complete")

    def phase_3_exploitation(self):
        """Phase 3: Vulnerability exploitation"""
        print("\n=== Phase 3: Exploitation ===")

        exploits = {
            'CAN': [
                {
                    'vulnerability': 'Unauthenticated CAN messages',
                    'exploit': 'Inject spoofed speedometer messages',
                    'tool': 'cansend',
                    'impact': 'HIGH',
                    'poc': 'cansend can0 1A0#0000C800000000  # 200 km/h fake speed'
                },
                {
                    'vulnerability': 'No rate limiting',
                    'exploit': 'CAN bus flooding (DoS)',
                    'tool': 'can-flood',
                    'impact': 'MEDIUM',
                    'poc': 'while true; do cansend can0 7FF#DEADBEEF; done'
                }
            ],
            'Bluetooth': [
                {
                    'vulnerability': 'Weak PIN pairing',
                    'exploit': 'Brute-force 4-digit PIN',
                    'tool': 'crackle',
                    'impact': 'HIGH',
                    'poc': 'for pin in {0000..9999}; do test_pair $pin; done'
                },
                {
                    'vulnerability': 'No encryption',
                    'exploit': 'Eavesdrop on Bluetooth LE traffic',
                    'tool': 'ubertooth-btle',
                    'impact': 'MEDIUM',
                    'poc': 'ubertooth-btle -f -c capture.pcap'
                }
            ],
            'OTA': [
                {
                    'vulnerability': 'No certificate pinning',
                    'exploit': 'MITM attack on firmware download',
                    'tool': 'mitmproxy',
                    'impact': 'CRITICAL',
                    'poc': 'mitmproxy -p 8080 --mode transparent'
                },
                {
                    'vulnerability': 'Missing signature verification',
                    'exploit': 'Flash unsigned firmware',
                    'tool': 'custom script',
                    'impact': 'CRITICAL',
                    'poc': 'flash_firmware.py --ecu TCU --file malicious.bin'
                }
            ],
            'Diagnostics': [
                {
                    'vulnerability': 'Weak seed-key algorithm',
                    'exploit': 'Calculate security access key',
                    'tool': 'seed-key-cracker',
                    'impact': 'HIGH',
                    'poc': 'crack_seed_key.py --seed 0x12345678'
                }
            ]
        }

        for attack_surface, exploit_list in exploits.items():
            if attack_surface in self.scope:
                print(f"\n[Exploiting {attack_surface}]")
                for exploit in exploit_list:
                    print(f"\n  Vulnerability: {exploit['vulnerability']}")
                    print(f"  Exploit: {exploit['exploit']}")
                    print(f"  Impact: {exploit['impact']}")
                    print(f"  PoC: {exploit['poc']}")

                    # Record finding
                    self.findings.append({
                        'attack_surface': attack_surface,
                        'vulnerability': exploit['vulnerability'],
                        'exploit_description': exploit['exploit'],
                        'tool': exploit['tool'],
                        'impact': exploit['impact'],
                        'poc': exploit['poc'],
                        'cvss_score': self._calculate_cvss(exploit['impact'])
                    })

        print("\n[INFO] Exploitation complete")

    def phase_4_post_exploitation(self):
        """Phase 4: Post-exploitation and lateral movement"""
        print("\n=== Phase 4: Post-Exploitation ===")

        post_exploit_actions = [
            {
                'goal': 'Privilege Escalation',
                'techniques': [
                    'Exploit buffer overflow in diagnostic handler',
                    'Bypass secure boot via bootloader vulnerability',
                    'Extract root shell from infotainment system'
                ]
            },
            {
                'goal': 'Lateral Movement',
                'techniques': [
                    'Pivot from infotainment to gateway ECU',
                    'Use compromised TCU to access CAN bus',
                    'Inject malicious gateway firmware update'
                ]
            },
            {
                'goal': 'Persistence',
                'techniques': [
                    'Install backdoor in bootloader',
                    'Modify OTA update server whitelist',
                    'Create rogue diagnostic service'
                ]
            },
            {
                'goal': 'Data Exfiltration',
                'techniques': [
                    'Extract V2X private keys from HSM',
                    'Dump telemetry data logs',
                    'Intercept GPS location history'
                ]
            }
        ]

        for action in post_exploit_actions:
            print(f"\n[{action['goal']}]")
            for technique in action['techniques']:
                print(f"  - {technique}")

        print("\n[INFO] Post-exploitation complete")

    def phase_5_reporting(self, output_file: str):
        """Phase 5: Generate penetration test report"""
        print("\n=== Phase 5: Reporting ===")

        report = {
            'executive_summary': {
                'target': self.target,
                'scope': self.scope,
                'test_date': self.start_time.strftime('%Y-%m-%d'),
                'total_findings': len(self.findings),
                'critical': sum(1 for f in self.findings if f['impact'] == 'CRITICAL'),
                'high': sum(1 for f in self.findings if f['impact'] == 'HIGH'),
                'medium': sum(1 for f in self.findings if f['impact'] == 'MEDIUM'),
                'low': sum(1 for f in self.findings if f['impact'] == 'LOW')
            },
            'findings': self.findings,
            'recommendations': self._generate_recommendations()
        }

        with open(output_file, 'w') as f:
            json.dump(report, f, indent=2)

        print(f"[INFO] Pentest report generated: {output_file}")

        # Print executive summary
        print(f"\n=== Executive Summary ===")
        print(f"Target: {report['executive_summary']['target']}")
        print(f"Total Findings: {report['executive_summary']['total_findings']}")
        print(f"  Critical: {report['executive_summary']['critical']}")
        print(f"  High: {report['executive_summary']['high']}")
        print(f"  Medium: {report['executive_summary']['medium']}")
        print(f"  Low: {report['executive_summary']['low']}")

        return report

    def _calculate_cvss(self, impact: str) -> float:
        """Calculate CVSS v3.1 score"""
        impact_scores = {
            'CRITICAL': 9.5,
            'HIGH': 7.8,
            'MEDIUM': 5.4,
            'LOW': 2.3
        }
        return impact_scores.get(impact, 0.0)

    def _generate_recommendations(self) -> List[Dict]:
        """Generate remediation recommendations"""
        recommendations = []

        # Group findings by attack surface
        for attack_surface in set(f['attack_surface'] for f in self.findings):
            surface_findings = [f for f in self.findings if f['attack_surface'] == attack_surface]

            if attack_surface == 'CAN':
                recommendations.append({
                    'attack_surface': 'CAN',
                    'remediation': 'Implement AUTOSAR SecOC for message authentication',
                    'priority': 'HIGH',
                    'effort': 'Medium (6-12 months)',
                    'cost': 'Medium ($500K - $1M)',
                    'standard': 'ISO 21434 Clause 9.4'
                })

            elif attack_surface == 'Bluetooth':
                recommendations.append({
                    'attack_surface': 'Bluetooth',
                    'remediation': 'Enforce Bluetooth LE Secure Connections (no legacy pairing)',
                    'priority': 'HIGH',
                    'effort': 'Low (1-3 months)',
                    'cost': 'Low ($50K - $100K)',
                    'standard': 'ISO 21434 Clause 9.5'
                })

            elif attack_surface == 'OTA':
                recommendations.append({
                    'attack_surface': 'OTA',
                    'remediation': 'Implement certificate pinning and firmware code signing',
                    'priority': 'CRITICAL',
                    'effort': 'Medium (3-6 months)',
                    'cost': 'Medium ($300K - $500K)',
                    'standard': 'UN R156 (OTA security requirements)'
                })

        return recommendations

# Example usage
if __name__ == "__main__":
    pentest = AutomotivePenTest(
        target_vehicle="2024 Electric SUV Model X",
        scope=['CAN', 'Bluetooth', 'OTA', 'Diagnostics']
    )

    # Execute pentest phases
    pentest.phase_1_reconnaissance()
    pentest.phase_2_scanning()
    pentest.phase_3_exploitation()
    pentest.phase_4_post_exploitation()

    # Generate report
    report = pentest.phase_5_reporting('/tmp/pentest_report.json')

    print("\n[COMPLETE] Penetration test finished")

Read the full file on GitHub · 742 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. 8d ago First seen · 742 lines · 33 tokens per session scan A b5d154f9b83a

Subscribe to this mod's changes

penetration-tester is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 5,881 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.