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.
npx skills add trilwu/secskills --skill analyzing-firmware-imagesgit clone --depth 1 https://github.com/trilwu/secskillsWrote 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/skills/trilwu/secskills/analyzing-firmware-images)<a href="https://agentmods.dev/skills/trilwu/secskills/analyzing-firmware-images"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/analyzing-firmware-images/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.
<a href="https://agentmods.dev/skills/trilwu/secskills/analyzing-firmware-images"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/analyzing-firmware-images.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.03819 |
| Opus 5 | $0.00046 | $0.01910 |
| Sonnet 5 | $0.00018 | $0.00764 |
| Haiku 4.5 | $0.00009 | $0.00382 |
Grade D, and why
analyzing-firmware-images scanned grade D with 2 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo chroot rootfs/ /usr/sbin/httpd Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
cat rootfs/etc/shadow How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing Firmware Images
Firmware is a frozen Linux (or RTOS) image, and its security froze with it. Hardcoded credentials, command injection in CGI scripts, unsigned update packages, and debug interfaces left enabled are not edge cases -- they are the baseline. The work is extraction, orientation, and then asking the same questions you would ask of any system, with the knowledge that nobody has patched this one since it shipped.
When to Use
- Extracting and analyzing a firmware update file (.bin, .img, .chk, .trx)
- Reviewing IoT device security posture from a firmware image
- Looking for hardcoded credentials, keys, or secrets in device firmware
- Assessing the attack surface of an embedded device or router
- Evaluating update mechanisms and signature verification
- Analyzing a bare-metal or RTOS image from a microcontroller
When NOT to Use
- Standard x86/x64 binary reverse engineering -- use
analyzing-binaries - Malware sample analysis -- use
analyzing-malware - Source code is available -- use
auditing-code-for-vulnerabilities
Firmware Acquisition
Before analysis comes acquisition. The method determines what you get.
| Method | What you get | Notes |
|---|---|---|
| Vendor download | Update package, often compressed or encrypted | Check support portals, FTP servers, and FCC filings |
| OTA sniffing | Update payload in transit | mitmproxy or tcpdump on the device's update channel; many devices use plain HTTP |
| UART/serial console | Shell access, bootloader interaction | Three wires (TX, RX, GND); identify with a multimeter or logic analyzer |
| JTAG/SWD | Full memory read, debug access | Requires pin identification; JTAGulator, OpenOCD |
| Chip-off | Raw flash contents (NAND/NOR) | Desolder the flash chip; read with a programmer (CH341A, FlashcatUSB); last resort |
| Bootloader extraction | Dump via U-Boot md or sf read commands |
If the bootloader shell is accessible over UART |
For OTA interception, configure the device to proxy through mitmproxy. Many devices ignore proxy settings -- ARP spoofing or a transparent bridge may be required. If the update is over HTTPS, check whether the device validates certificates at all; a surprising number do not.
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.
- 12d ago First seen · 381 lines · 91 tokens per session scan D 10d45ac46d14
analyzing-firmware-images is a skill published in the GitHub repository trilwu/secskills (138 stars, last pushed 7d ago), licensed MIT. It adds 91 tokens to every session and 3,819 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
code-review-facilitator
Automated code review for Arduino/ESP32/RP2040 projects focusing on best practices, memory safety, and common pitfalls. Use when user wants code feedback, says "review my code", needs help improving code quality, or before finalizing a project. Generates actionable checklists and specific improvement suggestions.
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.