Auditing Uefi Firmware With Chipsec logo

Auditing Uefi Firmware With Chipsec

CommunityPopular
mukul975
auditing-uefi-firmware-with-chipsec

Use Intel CHIPSEC to assess platform firmware configuration, SPI flash write protection, BIOS lock, SMM/SMRR, and Secure Boot variable state, dump SPI flash, and triage UEFI variables for firmware-level threats.

Overview

Publishermukul975
RepositoryAnthropic-Cybersecurity-Skills
Skill nameauditing-uefi-firmware-with-chipsec
Stars
34.3K
Forks
4.2K
Bundled files
3
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mukul975 on GitHub. Read the source before you install it.

Installation

Install the Auditing Uefi Firmware With Chipsec AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/auditing-uefi-firmware-with-chipsec
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git /tmp/Anthropic-Cybersecurity-Skills
mkdir -p .claude/skills
cp -r /tmp/Anthropic-Cybersecurity-Skills/skills/auditing-uefi-firmware-with-chipsec .claude/skills/auditing-uefi-firmware-with-chipsec
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Auditing Uefi Firmware With Chipsec in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Auditing Uefi Firmware With Chipsec on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Auditing Uefi Firmware With Chipsec is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Auditing UEFI Firmware with CHIPSEC

Authorized Use Only: CHIPSEC loads a kernel driver and reads/writes low-level hardware registers, SPI flash, and SMM. Run it only on systems you own or are explicitly authorized to assess, ideally on dedicated test hardware. Misuse (especially write/modify modules) can brick a machine. Never run write-capable modules on production systems.

Overview

CHIPSEC is the open-source Platform Security Assessment Framework created by Intel's Advanced Threat Research team. It inspects the low-level security configuration of x86 platform firmware and hardware — the layer below the operating system where bootkits and firmware implants live. CHIPSEC loads a signed kernel driver (Linux, Windows, or it can run from the UEFI shell) to read and write hardware registers, Model-Specific Registers (MSRs), PCI config space, SPI flash, and UEFI variables, then runs an automated test suite that checks whether the platform's defensive locks are actually engaged.

The threat CHIPSEC addresses is MITRE ATT&CK T1542.001 — Pre-OS Boot: System Firmware: adversaries who modify system firmware (the BIOS/UEFI image on SPI flash) to gain stealthy, persistent, OS-survivable control. Firmware implants persist across OS reinstall and disk replacement and are invisible to most EDR. CHIPSEC's value is verifying the prerequisites that prevent such implants: that the SPI flash BIOS region is write-protected (BIOS_CNTL BLE/SMM_BWP, SPI Protected Ranges), that the flash descriptor locks region access, that SMRAM/SMRR are configured, and that Secure Boot variables are protected. It also dumps the SPI flash for offline forensic comparison.

Sources: Intel/CHIPSEC project (https://github.com/chipsec/chipsec), CHIPSEC documentation (https://chipsec.github.io/).

When to Use

  • Baseline firmware-security assessment of a new laptop/server platform or fleet image
  • Verifying that BIOS write protection and SPI flash locks are correctly enabled by the OEM
  • Firmware forensics: dumping SPI flash to compare against a known-good image
  • Validating Secure Boot variable protection and S3 boot-script protection
  • Hunting for evidence of a firmware implant or misconfiguration enabling one

Prerequisites

  • Physical or admin/root access to the target x86 platform (Intel or AMD)
  • Linux (root) or Windows (Administrator), or a UEFI shell environment
  • Ability to load a kernel driver (Secure Boot may need to allow the CHIPSEC driver, or use --no_driver for limited checks)
  • Python 3.8+ and a C compiler/build tools for the kernel module on Linux
  • Dedicated test hardware strongly recommended

Install CHIPSEC:

bash
# From PyPI
pip install chipsec

# Or from source (builds the kernel helper/driver)
git clone https://github.com/chipsec/chipsec
cd chipsec
python setup.py install        # builds and installs, including the Linux driver

# Verify
sudo chipsec_main --help
sudo chipsec_util --help

Objectives

  • Run the full automated platform-security test suite and interpret PASS/FAIL/WARNING
  • Verify BIOS write protection (BIOS_CNTL) and SPI Protected Ranges
  • Verify the SPI flash descriptor locks region read/write access
  • Verify SMRAM/SMRR and SMI handler protections
  • Verify Secure Boot variable protection and S3 boot-script protection
  • Dump SPI flash and decode it for offline analysis
  • Enumerate UEFI variables and detect anomalous/unexpected entries

MITRE ATT&CK Mapping

Technique IDNameTactic
T1542.001Pre-OS Boot: System FirmwarePersistence / Defense Evasion

CHIPSEC defends against T1542.001 by verifying that the controls preventing unauthorized firmware modification are enabled. A FAIL on common.bios_wp (BIOS not write-protected) or chipsec.modules.common.spi_lock (flash descriptor unlocked) means an attacker with OS privileges could rewrite the SPI flash and implant persistent firmware — exactly the precondition for this technique.

Workflow

Step 1: Run the full automated test suite

chipsec_main with no module argument runs every applicable security check for the detected platform and prints a summary of PASS/FAIL/WARNING/INFORMATION results.

bash
sudo chipsec_main

# Save machine-readable output for reporting / diffing
sudo chipsec_main -j results.json -x results.xml -l chipsec.log

Step 2: Run the core firmware-protection modules individually

The common module group contains the OEM-independent security checks. Run the group or specific modules:

bash
# Run the whole common group
sudo chipsec_main -m common

# BIOS write protection: checks BIOS_CNTL BLE/SMM_BWP and SPI protected ranges
sudo chipsec_main -m common.bios_wp

# SPI flash descriptor lock (FLOCKDN) — are flash region accesses locked?
sudo chipsec_main -m common.spi_lock

# SMRR programming — protects SMRAM from cache-based attacks
sudo chipsec_main -m common.smrr

# SMM BIOS write protection
sudo chipsec_main -m common.smm

# S3 resume boot-script protection (against bootscript table attacks)
sudo chipsec_main -m common.uefi.s3bootscript

Step 3: Verify Secure Boot variable protection

bash
# Checks that Secure Boot UEFI variables are properly protected
sudo chipsec_main -m common.secureboot.variables

# To actively test write protection of the variables (test hardware ONLY):
sudo chipsec_main -m common.secureboot.variables -a modify

Step 4: Inspect SPI flash region access permissions

bash
# Report SPI flash regions, descriptor, and access permissions
sudo chipsec_util spi info

# Check the SPI access-control module
sudo chipsec_main -m common.spi_access

Step 5: Dump SPI flash for offline forensics

Dumping the flash lets you decode the firmware volumes and compare against a known-good OEM image.

bash
# Dump the entire SPI flash to a file
sudo chipsec_util spi dump rom.bin

# Decode the dumped image: extracts firmware volumes, files, NVRAM variables, etc.
sudo chipsec_util decode rom.bin

Step 6: Enumerate and triage UEFI variables

bash
# List all UEFI variables from the runtime interface
sudo chipsec_util uefi var-list

# List variables directly from the SPI image (offline)
sudo chipsec_util uefi var-find PK
sudo chipsec_util uefi var-read db <GUID> db.bin

# Decode the UEFI firmware structure
sudo chipsec_util uefi decode rom.bin

Step 7: Limited assessment without a kernel driver

Where loading the driver is impossible (locked-down Secure Boot), some checks still run read-only.

bash
sudo chipsec_main -n            # --no_driver: skip checks that need the driver
sudo chipsec_main -p <PLATFORM> # force platform code if auto-detect fails

Step 8: Triage results and report

  • FAIL on bios_wp / spi_lock → firmware is rewritable from the OS: high risk for T1542.001.
  • FAIL on secureboot.variables → Secure Boot policy can be tampered.
  • Compare the spi dump against the OEM's known-good image (hash firmware volumes) to detect unauthorized modification.
  • Record platform, BIOS version, and every FAIL/WARNING with the relevant register values for the report.

Tools and Resources

ToolPurposeSource
chipsec_mainAutomated platform-security test suitehttps://github.com/chipsec/chipsec
chipsec_utilManual hardware/firmware access (spi, uefi, decode)https://chipsec.github.io/
UEFIToolGUI/CLI parsing of dumped UEFI imageshttps://github.com/LongSoft/UEFITool
Binarly fwhuntFirmware vulnerability/implant hunting ruleshttps://github.com/binarly-io/fwhunt-scan
NSA UEFI Secure Boot guidanceHardening referencehttps://media.defense.gov/

Core Module Reference

ModuleChecks
common.bios_wpBIOS_CNTL BLE / SMM_BWP and SPI Protected Ranges
common.spi_lockSPI flash descriptor FLOCKDN
common.spi_accessSPI flash region read/write permissions
common.smrrSystem Management Range Registers programming
common.smmSMM BIOS write protection
common.secureboot.variablesSecure Boot variable protection
common.uefi.s3bootscriptS3 resume boot-script protection

Validation Criteria

  • CHIPSEC installed and driver loads (or -n documented if not)
  • Full chipsec_main suite executed with JSON/XML/log output saved
  • common.bios_wp result interpreted (write protection state)
  • common.spi_lock / spi_access result interpreted (descriptor lock)
  • SMRR/SMM module results recorded
  • Secure Boot variable protection checked
  • SPI flash dumped and decoded for offline analysis
  • UEFI variables enumerated and triaged
  • All FAIL/WARNING findings documented with platform/BIOS version
  • Write/modify modules NOT run on production hardware

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Auditing Uefi Firmware With Chipsec AI skill do?

Use Intel CHIPSEC to assess platform firmware configuration, SPI flash write protection, BIOS lock, SMM/SMRR, and Secure Boot variable state, dump SPI flash, and triage UEFI variables for firmware-level threats.

Why use Auditing Uefi Firmware With Chipsec on TypingMind?

Because you install it once and use it with any model. Auditing Uefi Firmware With Chipsec is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Auditing Uefi Firmware With Chipsec in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/auditing-uefi-firmware-with-chipsec. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Auditing Uefi Firmware With Chipsec?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Auditing Uefi Firmware With Chipsec?

As many as you like. As long as a model supports skills, you can use Auditing Uefi Firmware With Chipsec with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Auditing Uefi Firmware With Chipsec AI skill free?

Yes. It is published on GitHub by mukul975 under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇