Write Cve Rule
evdenis/cvehound
Write, debug, or validate a CVEhound detection rule (.cocci or .grep) for a Linux kernel CVE.
Detect UEFI Secure Boot bypasses and bootkits such as BlackLotus and Bootkitty by verifying Secure Boot state, checking dbx revocation currency, and hashing EFI boot binaries against known-bad sets…
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-secure-boot-bypass --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/detecting-secure-boot-bypass .claude/skills/detecting-secure-boot-bypass && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "detecting-secure-boot-bypass" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/detecting-secure-boot-bypass into .claude/skills/detecting-secure-boot-bypass/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detecting-secure-boot-bypass", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/detecting-secure-boot-bypassType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-secure-boot-bypass --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/detecting-secure-boot-bypass .agents/skills/detecting-secure-boot-bypass && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "detecting-secure-boot-bypass" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/detecting-secure-boot-bypass into .agents/skills/detecting-secure-boot-bypass/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detecting-secure-boot-bypass", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-secure-boot-bypass --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/detecting-secure-boot-bypass .cursor/skills/detecting-secure-boot-bypass && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "detecting-secure-boot-bypass" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/detecting-secure-boot-bypass into .cursor/skills/detecting-secure-boot-bypass/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detecting-secure-boot-bypass", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/detecting-secure-boot-bypass--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-secure-boot-bypass --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/detecting-secure-boot-bypass .gemini/skills/detecting-secure-boot-bypass && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "detecting-secure-boot-bypass" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/detecting-secure-boot-bypass into .gemini/skills/detecting-secure-boot-bypass/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detecting-secure-boot-bypass", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-secure-boot-bypassInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/detecting-secure-boot-bypass .github/skills/detecting-secure-boot-bypass && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "detecting-secure-boot-bypass" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/detecting-secure-boot-bypass into .github/skills/detecting-secure-boot-bypass/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detecting-secure-boot-bypass", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-secure-boot-bypass --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/detecting-secure-boot-bypass .opencode/skills/detecting-secure-boot-bypass && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "detecting-secure-boot-bypass" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/detecting-secure-boot-bypass into .opencode/skills/detecting-secure-boot-bypass/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "detecting-secure-boot-bypass", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
detecting-secure-boot-bypassDetect UEFI Secure Boot bypasses and bootkits such as BlackLotus and Bootkitty by verifying Secure Boot state, checking dbx revocation currency, and hashing EFI boot binaries against known-bad sets…
Detecting Secure Boot Bypass is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Detect UEFI Secure Boot bypasses and bootkits such as BlackLotus and Bootkitty by verifying Secure Boot state, checking dbx revocation currency, and hashing EFI boot binaries against known-bad sets using mokutil, efi-readvar/dbxtool, CHIPSEC, sbverify/pesign, and Windows Confirm-SecureBootUEFI. Use when auditing fleet dbx rollout after a bootkit advisory or hunting for pre-OS persistence on a suspected-compromised endpoint.
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/api-reference.md`, `references/standards.md` and `scripts/agent.py`).
It sits in Security. It works with Linux. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.
10 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
aptdnfpippythonFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comAlso links to:
uefi.orggit.kernel.orgsupport.microsoft.comwelivesecurity.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Detecting Secure Boot Bypass loads about 2.6k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 114 tokens; SKILL.md has 837 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
sudo apt install mokutil efitools sbsigntool dbxtool # Debian/Ubuntusudo dnf install mokutil efitools sbsigntools dbxtool # Fedora/RHELsudo chipsec_main -m common.secureboot.variablessudo chipsec_main -m common.uefi.s3bootscriptsudo chipsec_util spi dump rom.binsudo python scripts/agent.py --check-chipsec --output secureboot_report.jsonAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 837 words, ~2,564 tokens.
.claude/skills/detecting-secure-boot-bypass/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Legal Notice: Firmware and Secure Boot assessment must only be performed on systems you own or are explicitly authorized to test. CHIPSEC's write/modify modes and EFI variable manipulation can brick hardware. Run destructive checks only in a lab. This skill is for defensive verification and authorized assessment.
UEFI Secure Boot is the firmware-enforced trust chain that only permits boot components signed by keys in the platform's allow-list (db) and not present in the revocation list (dbx). Bootkits defeat this layer to gain pre-OS, persistent, kernel-level control that survives OS reinstalls and disk wipes. BlackLotus (2023) was the first publicly observed UEFI bootkit to bypass Secure Boot on fully patched Windows 11, abusing CVE-2022-21894 ("baton drop") in a vulnerable, signed Windows boot manager to neutralize Secure Boot and disable BitLocker, HVCI, and Defender. Bootkitty (2024) was the first PoC UEFI bootkit targeting Linux. Microsoft's CVE-2023-24932 addressed a related Secure Boot bypass that required a phased dbx (revocation) rollout because revoking the vulnerable boot managers can render systems unbootable if applied carelessly.
The core defensive insight is that patching the OS is not sufficient — the platform remains exploitable until the vulnerable, signed binaries are revoked in dbx. Detection therefore combines: (1) confirming Secure Boot is actually enabled, (2) verifying dbx is current and contains the relevant revocations, (3) checking the integrity and protection of Secure Boot EFI variables with CHIPSEC, (4) hashing on-disk EFI boot binaries and comparing them against the revocation list and known-bad sets, and (5) inspecting firmware/ESP for bootkit artifacts. This skill provides a cross-platform (Linux + Windows) workflow using mokutil, efi-readvar/dbxtool, chipsec, sbverify/pesign, and Windows Confirm-SecureBootUEFI / Get-SecureBootUEFI.
sudo apt install mokutil efitools sbsigntool dbxtool # Debian/Ubuntu
sudo dnf install mokutil efitools sbsigntools dbxtool # Fedora/RHELpip install chipsec # or build from https://github.com/chipsec/chipsecConfirm-SecureBootUEFI, Get-SecureBootUEFI), and optionally the UEFI dbx update package from Microsoft.dbxupdate files from https://uefi.org/revocationlistfile to compare against.| Technique ID | Technique Name | Relevance |
|---|---|---|
| T1542.003 | Pre-OS Boot: Bootkit | Core technique — bootkit subverts the boot chain below the OS. |
| T1542 | Pre-OS Boot | Parent technique covering firmware/boot-component tampering. |
| T1542.001 | Pre-OS Boot: System Firmware | Adjacent: firmware modification used to persist or weaken Secure Boot. |
| T1014 | Rootkit | Bootkits provide rootkit-level concealment and persistence. |
| T1562.001 | Impair Defenses: Disable or Modify Tools | BlackLotus disables BitLocker/HVCI/Defender after bypassing Secure Boot. |
A disabled or setup-mode platform offers no protection.
mokutil --sb-state # "SecureBoot enabled" expected
bootctl status | grep -i "secure boot" # systemd-boot view
# 6 = enabled+user mode on the EFI SecureBoot/SetupMode vars:
od -An -t u1 /sys/firmware/efi/efivars/SecureBoot-8be4df61-93ca-11d2-aa0d-00e098032b8cConfirm-SecureBootUEFI # $true if enabled
# Inspect the raw dbx variable from Windows:
[System.BitConverter]::ToString((Get-SecureBootUEFI dbx).bytes) | Out-File dbx.hexList db (allowed), dbx (revoked), KEK, and PK.
efi-readvar # dumps PK, KEK, db, dbx
efi-readvar -v dbx -o dbx.esl # export dbx to a file for offline analysis
mokutil --list-enrolled # MOK (shim) enrolled keys
mokutil --db # platform db entries via shimCompare on-system dbx to the current official UEFI revocation list.
dbxtool --list # current dbx entries + count
# Download latest dbxupdate from uefi.org/revocationlistfile, then:
dbxtool --dbx ./DBXUpdate.bin --apply --dry-run # show what WOULD be added (no write)A low dbx entry count or absence of recent revocations indicates the platform is behind and likely still vulnerable to known bypasses.
Verify the SB key variables are authenticated and not freely writable.
# Verify Secure Boot is enabled and the SB variables are properly protected:
sudo chipsec_main -m common.secureboot.variables
# Check S3 resume boot-script protections (an SMM/firmware bypass vector):
sudo chipsec_main -m common.uefi.s3bootscript
# Dump SPI flash for offline firmware diffing:
sudo chipsec_util spi dump rom.binVerify bootloaders are signed and not present in dbx.
# Locate and hash EFI boot binaries
find /boot/efi -iname '*.efi' -exec sha256sum {} \;
# Validate a binary's signature against the platform db
sbverify --list /boot/efi/EFI/BOOT/bootx64.efi
sbverify --cert /etc/secureboot/db.crt /boot/efi/EFI/Microsoft/Boot/bootmgfw.efi
# pesign equivalent on RHEL-family:
pesign -S -i /boot/efi/EFI/BOOT/bootx64.efiCompare collected hashes to revocation/known-bad sets (e.g., LoFP / vendor advisories).
# Example: confirm a binary's SHA-256 is NOT one of the revoked CVE-2022-21894 boot managers
sha256sum /boot/efi/EFI/Microsoft/Boot/bootmgfw.efi
# Compare against the hash list extracted from the latest dbxupdate / advisory.Look for unauthorized ESP modifications and self-deployment markers.
# Unexpected files / recently modified binaries on the ESP
ls -laR /boot/efi/EFI/
find /boot/efi -newermt "-30 days" -iname '*.efi'
# On Windows, examine the EFI partition for rogue \EFI\Microsoft\Boot entries.If a TPM is present, current PCR[7] reflects Secure Boot policy; deviations corroborate tampering.
tpm2_pcrread sha256:7 # Secure Boot policy PCRagent.py collects SB state, dbx counts, ESP binary hashes, and CHIPSEC results into one report.
sudo python scripts/agent.py --check-chipsec --output secureboot_report.json| Tool | Purpose | Source |
|---|---|---|
| mokutil | Secure Boot state and enrolled keys (Linux) | https://github.com/lcp/mokutil |
| efitools (efi-readvar) | Dump PK/KEK/db/dbx | https://git.kernel.org/pub/scm/linux/kernel/git/jejb/efitools.git |
| dbxtool | Inspect and apply dbx updates | https://github.com/rhboot/dbxtool |
| CHIPSEC | Firmware / Secure Boot variable assessment | https://github.com/chipsec/chipsec |
| sbsigntool / pesign | EFI binary signature verification | https://github.com/jejb/sbsigntools |
| UEFI Revocation List | Official dbx update files | https://uefi.org/revocationlistfile |
| Microsoft KB CVE-2023-24932 | Secure Boot bypass guidance | https://support.microsoft.com/topic/kb5025885 |
| ESET BlackLotus analysis | Bootkit technical writeup | https://www.welivesecurity.com/2023/03/01/blacklotus-uefi-bootkit-myth-confirmed/ |
secureboot.variables and s3bootscript modules run.© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (scripts, references) in skills/detecting-secure-boot-bypass of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Detecting Secure Boot Bypass next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Detecting Secure Boot Bypass this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.6k | Automated safety check: Notes | Apache-2.0 | |
| Write Cve Ruleevdenis/cvehound | 138 | — | ~2.5k | Automated safety check: Pass | GPL-3.0 | |
| Securitystatic-web-server/static-web-server | 2.4k | — | ~1.5k | Automated safety check: Notes | Apache-2.0 | |
| User Managementsickn33/agentic-awesome-skills | 47k | 2 repos | ~2.8k | Automated safety check: Notes | MIT | |
| Memory Dumperptn1411/skill | 220 | — | ~945 | Automated safety check: Notes | None | |
| Patt Fetchertransilienceai/communitytools | 562 | — | ~1.3k | Automated safety check: Pass | MIT |
evdenis/cvehound
Write, debug, or validate a CVEhound detection rule (.cocci or .grep) for a Linux kernel CVE.
static-web-server/static-web-server
Review or implement security measures for the Static Web Server (SWS) project — path traversal prevention, TLS, security headers, CORS, and input validation
sickn33/agentic-awesome-skills
Manage users, groups, and permissions on Linux systems. An agent skill from sickn33/agentic-awesome-skills.
ptn1411/skill
Dump process memory and scan for secrets, license keys, decryption keys, tokens, and crypto artifacts.
transilienceai/communitytools
Fetches and extracts payloads from PayloadsAllTheThings on demand.
dslsdzc/rev-skills
威胁情报查询与关联:VT/Any.run/hybrid-analysis、MISP. An agent skill from dslsdzc/rev-skills.
mukul975/Anthropic-Cybersecurity-Skills
Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.
mukul975/Anthropic-Cybersecurity-Skills
Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.
mukul975/Anthropic-Cybersecurity-Skills
Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.
mukul975/Anthropic-Cybersecurity-Skills
Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.
mukul975/Anthropic-Cybersecurity-Skills
Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.
mukul975/Anthropic-Cybersecurity-Skills
Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.
Works with
Categories
Detect UEFI Secure Boot bypasses and bootkits such as BlackLotus and Bootkitty by verifying Secure Boot state, checking dbx revocation currency, and hashing EFI boot binaries against known-bad sets…. Detecting Secure Boot Bypass is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Detect UEFI Secure Boot bypasses and bootkits such as BlackLotus and Bootkitty by verifying Secure Boot state, checking dbx revocation currency, and hashing EFI boot binaries against known-bad sets using mokutil, efi-readvar/dbxtool, CHIPSEC, sbverify/pesign, and Windows Confirm-SecureBootUEFI.
Detecting Secure Boot Bypass fits situations like: auditing fleet dbx rollout after a bootkit advisory; hunting for pre-OS persistence on a suspected-compromised endpoint.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a claude-code`. Or copy the skill folder (skills/detecting-secure-boot-bypass in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/detecting-secure-boot-bypass in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a codex`. Or copy the skill folder (skills/detecting-secure-boot-bypass in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/detecting-secure-boot-bypass in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-secure-boot-bypass -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/detecting-secure-boot-bypass, .gemini/skills/detecting-secure-boot-bypass, .github/skills/detecting-secure-boot-bypass and .opencode/skills/detecting-secure-boot-bypass in your project.
Going by SKILL.md and its folder, Detecting Secure Boot Bypass needs Python for the scripts in its folder and the command-line tools its instructions call (apt, dnf, pip and python). Our summary lists: Python 3.
SKILL.md names 5 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: uefi.org, git.kernel.org, support.microsoft.com and welivesecurity.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Detecting Secure Boot Bypass is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 951 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Detecting Secure Boot Bypass: Write Cve Rule (evdenis/cvehound, 138 stars), Security (static-web-server/static-web-server, 2.4k stars), User Management (sickn33/agentic-awesome-skills, 47k stars) and Memory Dumper (ptn1411/skill, 220 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 33,993 GitHub stars. The repository holds 644 skills in this directory. The repository was last updated on August 31, 2026.
Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.