firmware-analyst

firmware-analyst is a skill for Claude Code, Codex from rmyndharis/antigravity-skills. It costs 66 tokens per session (1,869 once invoked), scanned A, original, MIT.

A firmware-analysis guide for examining the software stored on embedded devices such as routers, IoT products, vehicles, and industrial controllers. It covers extracting firmware from vendors, networks, debug interfaces, and memory chips.

In plain words
What is it for?
Use it to extract firmware, inspect files and partitions, work with UART, JTAG, SWD, SPI, NAND, and NOR interfaces, and perform embedded-device security research.
Why use it?
It helps security researchers inspect device software for weaknesses when the source code is unavailable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract firmware, inspect files and partitions, work with UART, JTAG, SWD, SPI, NAND, and NOR interfaces, and perform embedded-device security research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rmyndharis/antigravity-skills/firmware-analyst
About the project

Antigravity Skill Vault is a collection of reusable Agent Skills for Google Antigravity, covering software development, operations, security, and business work. It is for people who want Antigravity agents to follow specialized expertise, personas, and structured workflows. The catalogue skills are entries from this collection.

rmyndharis/antigravity-skills · 1,529 stars · on GitHub

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.

Any agent
npx skills add rmyndharis/antigravity-skills --skill firmware-analyst
Clone the repo
git clone --depth 1 https://github.com/rmyndharis/antigravity-skills

Made for: Claude Code, Codex.

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 firmware-analyst

README.md
[![agentmods](https://agentmods.dev/badge/skills/rmyndharis/antigravity-skills/firmware-analyst/github.svg)](https://agentmods.dev/skills/rmyndharis/antigravity-skills/firmware-analyst)
Your own site
<a href="https://agentmods.dev/skills/rmyndharis/antigravity-skills/firmware-analyst"><img src="https://agentmods.dev/badge/skills/rmyndharis/antigravity-skills/firmware-analyst/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 firmware-analyst

Your own site · 80×15
<a href="https://agentmods.dev/skills/rmyndharis/antigravity-skills/firmware-analyst"><img src="https://agentmods.dev/badge/skills/rmyndharis/antigravity-skills/firmware-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 158
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Privilege Escalation · line 230
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 233
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
How audits are shown
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 $0.00066 $0.01869
Opus 5 $0.00033 $0.00934
Sonnet 5 $0.00013 $0.00374
Haiku 4.5 $0.00007 $0.00187

Measured 8d ago against content hash 833c3710f0fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

firmware-analyst scanned grade A 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 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo chroot squashfs-root /usr/bin/qemu-arm-static /bin/sh

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

wget http://vendor.com/firmware/update.bin
skills/firmware-analyst/SKILL.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Download from vendor

wget http://vendor.com/firmware/update.bin

Extract from device via debug interface

UART console access

screen /dev/ttyUSB0 115200

Copy firmware partition

dd if=/dev/mtd0 of=/tmp/firmware.bin

Extract via network protocols

TFTP during boot

HTTP/FTP from device web interface


### Hardware Methods

UART access - Serial console connection JTAG/SWD - Debug interface for memory access SPI flash dump - Direct chip reading NAND/NOR dump - Flash memory extraction Chip-off - Physical chip removal and reading Logic analyzer - Protocol capture and analysis


## Use this skill when

- Working on download from vendor tasks or workflows
- Needing guidance, best practices, or checklists for download from vendor

## Do not use this skill when

- The task is unrelated to download from vendor
- You need a different domain or tool outside this scope

## Instructions

- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.

## Firmware Analysis Workflow

### Phase 1: Identification
```bash
# Basic file identification
file firmware.bin
binwalk firmware.bin

# Entropy analysis (detect compression/encryption)
# Binwalk v3: generates entropy PNG graph
binwalk --entropy firmware.bin
binwalk -E firmware.bin  # Short form

# Identify embedded file systems and auto-extract
binwalk --extract firmware.bin
binwalk -e firmware.bin  # Short form

# String analysis
strings -a firmware.bin | grep -i "password\|key\|secret"

Phase 2: Extraction

# Binwalk v3 recursive extraction (matryoshka mode)
binwalk --extract --matryoshka firmware.bin
binwalk -eM firmware.bin  # Short form

# Extract to custom directory
binwalk -e -C ./extracted firmware.bin

# Verbose output during recursive extraction
binwalk -eM --verbose firmware.bin

# Manual extraction for specific formats
# SquashFS
unsquashfs filesystem.squashfs

Read the full file on GitHub · 320 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 · 320 lines · 66 tokens per session scan A 833c3710f0fc

Subscribe to this mod's changes

firmware-analyst is a skill published in the GitHub repository rmyndharis/antigravity-skills (1,529 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,869 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

analyzing-usb-device-connection-history

Investigate USB device connection history from Windows registry, event logs, and setupapi logs to track removable media usage and potential data exfiltration.

marysatasselshaped667/skills-collection-1 · 39 tokens

bluetooth-expert

Professional Bluetooth Expert skill. Build performance-tuned, secure, and intuitive mobile applications for iOS and Android.

AtulPurohit/Antigravity-Awesome-Skills · 27 tokens

arm-cortex-expert

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD).

marysatasselshaped667/skills-collection-1 · 37 tokens

Arm Cortex Expert

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…

mayurrathi/awesome-agent-skills · 70 tokens

bolt-iot-automation

Automate Bolt Iot tasks via Rube MCP (Composio). Always search tools first for current schemas.

ComposioHQ/awesome-claude-skills · 29 tokens

code-review

Systematic code review skill covering both requesting a review (pre-commit checklist) and receiving and responding to review feedback. Checks code quality, security, test coverage, architectural alignment, and documentation before any code is committed.

omergocmen/vibe-coder-kit · 47 tokens