security-review SKILL.md skillA

security-review from patrickserrano/lacquer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add patrickserrano/lacquer/security-review@git:20260712.d1d6fca

Pins git:20260712.d1d6fca in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
patrickserrano/lacquer
Path
core/skills/security-review/SKILL.md
Versions recorded
2
Latest version
git:20260712.d1d6fca, committed Jul 12, 2026
First version recorded
Jul 8, 2026
Size
2,888 bytes
Repository stars
5
License
MIT

Adversarial security review of a change (branch diff, PR, or working tree) before merge. Use when the user asks to "review this for security", "security review", "check for vulnerabilities", "is this safe to merge", or before merging anything that touches a trust boundary — auth/authz, input parsing, secrets/keychains, file writes, shelling out, untrusted-input-into-shell/YAML, CI workflows that run on privileged runners, or generated LLM instructions. Also the standing gate this repo runs on…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

Review the change adversarially — assume the diff is hostile until proven safe. Report
only findings you can tie to a concrete failure scenario; do not pad with generic advice.

## Scope the diff

1. Establish the base: `git diff <base>...HEAD` for a branch, `gh pr diff <n>` for a PR,
   or `git diff` for the working tree. Read enough surrounding context to judge each hunk —
   never review a hunk in isolation.
2. If the change is large, fan out: one reviewer per trust boundary (auth, input parsing,
   secrets, CI/exec, file I/O), then dedupe. A single pass misses cross-cutting issues.

## What to hunt for

- **Injection**: untrusted input (user data, `github.event.*`, PR titles/branch names,
  file contents, tool output, dependency changelogs) reaching a shell, `eval`, SQL, YAML,
  or an LLM instruction context. Trace the value from source to sink; quote both.
- **Path/traversal & symlink**: writes that can escape a root, TOCTOU between check and
  write, following a symlink, absolute paths sneaking in through a config field.
- **Secrets**: keys/tokens echoed, written to files that become artifacts, passed on a
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add patrickserrano/lacquer/security-review@sha256:160dfedbdb22deb2

The line at the top of this page pins the label git:20260712.d1d6fca, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7tam265jbq6jtths.svg)](https://markdownregistry.com/a/art_7tam265jbq6jtths)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jul 8, 2026 and Jul 12, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20260712.d1d6fca latest2026-07-12 d1d6fca 2,888 BA view · diff
git:20260708.cd5aa362026-07-08 cd5aa36 2,888 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2888 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

patrickserrano/lacquer · 5 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7tam265jbq6jtths
GET https://markdownregistry.com/api/v1/resolve?ref=patrickserrano/lacquer/security-review
GET https://markdownregistry.com/api/v1/blob/160dfedbdb22deb240a3fc3d57595eb2b3e6fde57e053f930f75de43584a1b34

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from patrickserrano/lacquer

CLAUDE.md CLAUDE.md file
patrickserrano/lacquer · CLAUDE.md
git:20261012.ee749bd · audit A · 5 stars
advisor-checkpoint SKILL.md skill
patrickserrano/lacquer · core/skills/advisor-checkpoint/SKILL.md · Consult a stronger model mid-task for a second opinion before committing to an approach, when stuck, or before…
git:20260725.3f0d943 · audit A · 5 stars
antigravity-rescue SKILL.md skill
patrickserrano/lacquer · core/skills/antigravity-rescue/SKILL.md · Use when stuck, wanting a second implementation or diagnosis pass, or handing a substantial task to Google's…
git:20260713.797aca7 · audit A · 5 stars
caveman SKILL.md skill
patrickserrano/lacquer · core/skills/caveman/SKILL.md · Use when the user says "caveman mode", "talk like caveman", "use caveman", "less tokens", or "be brief", invokes…
git:20260725.3f0d943 · audit A · 5 stars
claude-rescue SKILL.md skill
patrickserrano/lacquer · core/skills/claude-rescue/SKILL.md · Use when running under Codex CLI and stuck, wanting a second implementation or diagnosis pass, or handing a substantial…
git:20260713.e9a0b7c · audit A · 5 stars
claudemd-review SKILL.md skill
patrickserrano/lacquer · core/skills/claudemd-review/SKILL.md · Use right after being corrected on something a CLAUDE.md file should already have told you, when explicitly asked to…
git:20260725.3f0d943 · audit A · 5 stars
engineering-workflow SKILL.md skill
patrickserrano/lacquer · core/skills/engineering-workflow/SKILL.md · Implement a feature, review a change, delegate work, or resume a session in a Lacquer-managed project.
git:20260924.6411787 · audit A · 5 stars
evaluator-optimizer SKILL.md skill
patrickserrano/lacquer · core/skills/evaluator-optimizer/SKILL.md · Generate a solution, evaluate it against explicit pass/fail criteria, refine using the feedback, repeat until it passes…
git:20260725.3f0d943 · audit A · 5 stars
exploring-an-idea SKILL.md skill
patrickserrano/lacquer · core/skills/exploring-an-idea/SKILL.md · Use at the very start of a new product idea — before a PRD, PCD, repo, or name exists, and any time someone says "I…
git:20261009.58faf9c · audit A · 5 stars
github-ci-fix SKILL.md skill
patrickserrano/lacquer · core/skills/github-ci-fix/SKILL.md · Fix failing PR checks, debug GitHub Actions, or account for CI follow-up rounds and wait for verification.
git:20260924.6411787 · audit A · 5 stars
github-issue-fix-flow SKILL.md skill
patrickserrano/lacquer · core/skills/github-issue-fix-flow/SKILL.md · Use when asked to take a GitHub issue number, implement a fix, run builds/tests, commit with a closing message, and…
git:20260713.c1007fc · audit A · 5 stars
handoff SKILL.md skill
patrickserrano/lacquer · core/skills/handoff/SKILL.md · Write a structured handoff document before a session ends, before a context-heavy interruption (SSH/tmux disconnect…
git:20260725.3f0d943 · audit A · 5 stars

Every file in patrickserrano/lacquer

Other files named security-review

security-review SKILL.md skill
affaan-m/ecc · .agents/skills/security-review/SKILL.md · Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or…
git:20260918.c752aac · audit A · 299,696 stars
security-review SKILL.md skill
affaan-m/ecc · .kiro/skills/security-review/SKILL.md · Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or…
git:20260330.866d9eb · audit A · 299,696 stars
security-review SKILL.md skill
affaan-m/ecc · docs/es/skills/security-review/SKILL.md · Usar este skill al agregar autenticación, manejar entradas de usuario, trabajar con secretos, crear endpoints de API o…
git:20260607.ac0f11c · audit A · 299,696 stars
security-review SKILL.md skill
bradygaster/squad · .copilot/skills/security-review/SKILL.md · How to review PRs for security — credentials, injection, workflow permissions, supply chain, git operation safety
git:20260403.003f05f · audit A · 3,337 stars
security-review SKILL.md skill
a5c-ai/babysitter · library/methodologies/rpikit/skills/security-review/SKILL.md · Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure…
git:20260601.da7723a · audit A · 1,896 stars
security-review SKILL.md skill
codeaholicguy/ai-devkit · skills/security-review/SKILL.md · AI DevKit · Review code, skills, and prompts for security vulnerabilities — OWASP Top 10, prompt injection, business…
git:20260509.950097b · audit A · 1,661 stars
security-review SKILL.md skill
microsoft/power-platform-skills · plugins/power-pages/skills/security-review/SKILL.md · Runs a guided, end-to-end security review of a Power Pages site and consolidates every finding into one HTML report…
git:20260716.1dcf201 · audit A · 1,123 stars
security-review SKILL.md skill
kklimuk/docx-cli · .claude/skills/security-review/SKILL.md · Review code for security vulnerabilities. Use when the user says 'security review', 'security audit', 'check for…
git:20260630.4ec3889 · audit A · 242 stars

Browse by kind, by grade A, or by owner.