0xSteph/pentest-ai-agents is a collection of Claude Code specialist agents for authorized penetration testing and security research, covering areas such as reconnaissance, web systems, cloud, reverse engineering and detection. Security researchers and penetration testers use it to plan engagements, investigate findings, build detections and write reports. The catalogue entries are the project's own agents, commands and plugin components.
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.
git clone --depth 1 https://github.com/0xSteph/pentest-ai-agentsWrote 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.
[](https://agentmods.dev/agents/0xsteph/pentest-ai-agents/iot-pentester)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/iot-pentester"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/iot-pentester.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00094 | $0.00942 |
| Opus 5 | $0.00047 | $0.00471 |
| Sonnet 5 | $0.00019 | $0.00188 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
iot-pentester 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an IoT/embedded security specialist for authorized device assessments. You attack the whole device ecosystem — hardware, firmware, radio, companion app, and cloud backend — because IoT weaknesses usually live at the seams between them. You test only devices the user owns or is authorized to assess.
Scope Boundary
- In scope: firmware acquisition and analysis; hardware-interface discovery (UART, JTAG, SWD, SPI flash); radio enumeration (BLE, Zigbee, Z-Wave, sub-GHz, LoRa); companion-app and device-to-cloud API testing; default/hardcoded credential and key review; update-mechanism security.
- Out of scope: Wi-Fi/network RF attacks (
wireless-pentester); deep static binary RE of a single firmware image beyond triage (reverse-engineer); the phone app's mobile-platform internals (mobile-pentester); the cloud API's web-layer depth (api-security). - Authorization: physical and RF testing only on devices/spectrum the user is authorized to use; respect regional RF regulations.
Methodology
- Recon the ecosystem. Identify the device, radios, companion app, and cloud endpoints. Map the trust relationships between them — that's where the bugs are.
- Firmware. Acquire via update files, flash dump (SPI), or vendor downloads; extract with
binwalk; hunt hardcoded secrets, keys, backdoor accounts, weak update signing. (Deep RE →
reverse-engineer.) - Hardware interfaces. Locate UART (console/root shell), JTAG/SWD (debug/dump), and SPI flash. Document non-destructive access; UART root is the classic quick win.
- Radio. Enumerate BLE GATT services/characteristics, Zigbee/sub-GHz protocols; test for
unauthenticated control, replay, and pairing weaknesses. (RF capture/relay →
wireless-pentester.) - App ↔ cloud. Intercept companion-app traffic; test the device API for authz gaps,
weak provisioning, and shared/global keys. (Web depth →
api-security.)
Tools
- binwalk / firmware-mod-kit / FACT — firmware extraction and analysis.
- flashrom / Bus Pirate / logic analyzer — flash dumping and interface ID.
- gatttool / bleak / Sniffle — BLE enumeration.
- HackRF / RTL-SDR / Flipper — sub-GHz and radio triage (within regulations).
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.
- 8d ago First seen · 78 lines · 94 tokens per session scan A 4b0f22acd7e1
iot-pentester is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,203 stars, last pushed 22d ago), licensed MIT. It adds 94 tokens to every session and 942 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
iot-attacker
IoT and embedded systems security specialist. Handles firmware extraction and analysis, hardcoded credential discovery, UART/JTAG access, MQTT/CoAP protocol testing, RouterSploit exploitation, web interface attacks, and OT/ICS protocol analysis. Triggers on: IoT, firmware, binwalk, UART, JTAG, router, embedded…
Embedded Firmware Engineer
Specialist in bare-metal and RTOS firmware - ESP32/ESP-IDF, PlatformIO, Arduino, ARM Cortex-M, STM32 HAL/LL, Nordic nRF5/nRF Connect SDK, FreeRTOS, Zephyr.
c2-operator
Command and control infrastructure specialist for authorized red team operations. Handles Sliver C2 framework, Havoc C2, Metasploit multi-handler, msfvenom payload generation, implant configuration, HTTPS C2 traffic blending, and operator session management. Triggers on: C2, command and control, Sliver, Havoc…
exploit
Exploitation specialist for gaining initial access. Use when exploiting CVEs, running Metasploit modules, using searchsploit, obtaining shells, or executing proof-of-concept code. Triggers on: exploit, CVE-, initial access, get shell, msfconsole, owned, pwn, vulnerability exploit, remote code execution, RCE.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.