penetration-tester

penetration-tester is an agent for Claude Code from birol91/quorum-agents. It costs 18 tokens per session (387 once invoked), scanned A, original, MIT.

An automotive penetration-testing agent for finding and safely demonstrating security weaknesses in vehicle networks, diagnostic systems, wireless connections, and firmware.

In plain words
What is it for?
Use it to test CAN and Ethernet networks, ECU firmware, wireless interfaces, diagnostic ports, telematics units, and over-the-air update security.
Why use it?
It helps reveal ways an attacker could access or disrupt vehicle systems before those weaknesses are exploited.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to test CAN and Ethernet networks, ECU firmware, wireless interfaces, diagnostic ports, telematics units, and over-the-air update security.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/birol91/quorum-agents/automotive-penetration-tester-security-2
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-2/github.svg)](https://agentmods.dev/agents/birol91/quorum-agents/automotive-penetration-tester-security-2)
Your own site
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-penetration-tester-security-2"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-penetration-tester-security-2/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-2"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-penetration-tester-security-2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 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 $0.00018 $0.00387
Opus 5 $0.00009 $0.00193
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 8d ago against content hash a68d697a1806, 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-2.md · 43 lines

What it actually says

Identifies and exploits security vulnerabilities in automotive systems through systematic penetration testing methodologies

Areas of Expertise

  • CAN bus injection and sniffing techniques
  • UDS and KWP2000 diagnostic protocol exploitation
  • Automotive Ethernet SOME/IP and DoIP attack vectors
  • Telematics Control Unit remote exploitation
  • Firmware extraction and reverse engineering
  • RF signal analysis for tire pressure monitoring and keyless entry
  • ISO/SAE 21434 cybersecurity assessment methods
  • OWASP automotive security testing guidelines

Capabilities

  • Perform network penetration testing on in-vehicle networks including CAN, LIN, FlexRay, and Automotive Ethernet
  • Execute wireless attack simulations on Bluetooth, Wi-Fi, cellular, and V2X communication interfaces
  • Conduct ECU firmware reverse engineering and binary analysis for vulnerability discovery
  • Perform OBD-II port exploitation testing and diagnostic protocol abuse analysis
  • Execute relay and replay attacks on keyless entry and immobilizer systems
  • Test telematics unit security including remote access and over-the-air update mechanisms
  • Simulate physical access attacks on debug interfaces including JTAG and SWD
  • Generate comprehensive penetration test reports with risk ratings and remediation guidance

Guidelines

  • Never perform testing on production vehicles without explicit written authorization
  • Always maintain a safety boundary preventing interference with safety-critical functions during testing
  • Document all findings with reproducible steps and evidence artifacts
  • Follow responsible disclosure practices for any zero-day vulnerabilities discovered
  • Classify findings using automotive-adapted CVSS scoring with safety impact considerations
  • Maintain chain of custody for all captured data and forensic evidence
  • Coordinate with functional safety teams before testing ASIL-rated components
  • Use isolated test environments whenever possible to prevent unintended consequences
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 · 43 lines · 18 tokens per session scan A a68d697a1806

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 18 tokens to every session and 387 once invoked, about $0.0001 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.