Agent skill · Audited from source

woo-guard

skill · amelnagdy/guard-skillsMIT licenceAudited 23 Oct 2026 · source e749c40f6229

★ 1,279pushed 110 days ago
✓SAFEGrade B · 89/100 · 23 Oct 2026 · e749c40
1,279repo stars · whole amelnagdy/guard-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit e749c40f6229 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Review generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “woo-guard (amelnagdy/guard-skills)”. Retrieved 23 Oct 2026. https://modelsatlas.com/skills/amelnagdy/woo-guard

Trust audit

Audit 0.4.1 · source read 23 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha e749c40f6229 · 23 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheramelnagdy GitHub userOwner of the repository this skill is read from
  • Source folderamelnagdy/guard-skills/skills/woo-guardThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicte749c40f6229A new audit runs when the source changes
  • Repository statusNot archivedLast push 110 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Review generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or…

---
name: woo-guard
description: "Review generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WooCommerce APIs: wc_get_order, wc_get_orders, wc_get_product, WC() cart or session, woocommerce_* hooks, Store API endpoints, payment gateways, order or product meta, HPOS, subscriptions, or bookings. Use on 'review this Woo plugin', 'is this HPOS compatible', or after tasks like 'write a WooCommerce extension', 'add a checkout field', 'hook into the order flow', or 'update stock'. Enforces HPOS-safe order access, CRUD over direct meta, feature-compatibility declarations, server-side checkout validation, money-handling discipline, and hooks over template overrides. DO NOT USE for WordPress code without WooCommerce APIs (use wp-guard), generic code review (use clean-code-guard), test review (use test-guard), or store configuration and admin-screen questions."
---

# Woo Guard

You are reviewing generated or changed WooCommerce code before it ships. Apply the rules below as a guard pass after the first implementation pass. WooCommerce is a moving platform — order storage changed engines, checkout changed frameworks — and code written from memory targets the WooCommerce of three years ago. With money on the line, "works on my demo store" is not a standard.

These rules exist because AI agents produce WooCommerce code with systematic failures: order meta read through `get_post_meta()` (broken on HPOS stores), products updated by direct meta writes that skip lookup tables and hooks, checkout validated only in JavaScript, prices computed in floats, and `woocommerce_*` hooks registered before confirming WooCommerce is active.

## How to use this skill

**Guard-pass mode** (recommended): after WooCommerce code has been generated or edited, apply the rules to the diff or target files, then run the self-check before delivery.

**Live mode** (explicit): when the user invokes this skill before writing WooCommerce code, apply the same rules while writing, then run the self-check before delivery.

**Review mode** (the user asks you to review or audit WooCommerce code): walk [references/review-checklist.md](references/review-checklist.md) and produce a structured findings report. Do not edit code in review mode unless asked.

**Security floor** — these hold in all WooCommerce code, at maximum severity, because money is on the line:

- Escape all output with the context-correct `esc_*` function.
- `wp_unslash()` then sanitize all request data before it touches logic.
- Capability check plus nonce on every state change.
- `$wpdb->prepare()` for every query containing a variable.

If wp-guard is installed, run it alongside for the full WordPress layer.

## Adapt to the project first

1. Read the project's agent instructions and the extension's declared WooCommerce version range. Project conventions win on conflict.
2. Determine the order storage mode this code must support: HPOS, legacy posts, or both (the default assumption is both).
3. Determine the checkout in play: Blocks/Store API, legacy shortcode checkout, or both. Hooks for one do not fire in the other.
4. Check whether WooCommerce activity is guarded: feature checks or `class_exists( 'WooCommerce' )` before any `wc_*` call or `woocommerce_*` hook.

## The Rules

### Order and product data — must fix

1. **Orders are not posts.** Access orders only through the CRUD API: `wc_get_order()`, `wc_get_orders()`, `$order->get_meta()`, `$order->update_meta_data()` + `$order->save()`. Forbidden on order data: `get_post_meta()`, `update_post_meta()`, `WP_Query`/`get_posts()` with `post_type => shop_order`, and direct `$wpdb` joins on postmeta. These work on legacy stores and silently break on HPOS stores. Details: [references/hpos-and-crud.md](references/hpos-and-crud.md).

2. **CRUD objects, getters/setters, then save.** Products, customers, and coupons go through their CRUD objects (`wc_get_product()`, setters, `->save()`). Direct meta writes skip lookup-table sync, skip the hooks other extensions rely on, and skip cache invalidation. Stock changes go through `wc_update_product_stock()` semantics; order state changes through `$order->update_status()` — which fire the emails and hooks the store expects.

3. **Declare feature compatibility.** Any extension touching orders declares HPOS compatibility (`FeaturesUtil::declare_compatibility( 'custom_order_tables', ... )`); any extension touching checkout declares `cart_checkout_blocks` compatibility (or incompatibility, honestly). A missing declaration shows every store owner a warning banner with your plugin's name on it.

### Checkout and money — must fix

4. **Checkout validation is server-side.** Validate at `woocommerce_checkout_process` (legacy) or through Store API extension schemas (Blocks). JavaScript validation is UX, never security. Know which checkout the store runs and wire both when the extension claims general compatibility.

5. **Money is not a float.** Prices and totals go through `wc_format_decimal()` for storage-safe values, `wc_price()` for display, and WooCommerce's own tax/rounding settings for arithmetic. No hand-rolled currency symbols, no `number_format()` on prices, no float equality on totals.

### Runtime discipline — should fix

6. **Guard the runtime context.** `WC()->cart` and `WC()->session` are null in REST, cron, CLI, and admin contexts — check before touching them. Never assume a logged-in customer in webhook or gateway callbacks. Verify every `woocommerce_*` hook and `wc_*` function exists in the supported version range — WooCommerce renames and retires hooks across majors.

7. **Hooks over template overrides.** Prefer, in order: existing WooCommerce hooks/filters → the `woocommerce_locate_template` filter → a theme-level override. A template override shipped inside a plugin freezes a copied file at one WooC

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit e749c40

Download folder ↗
git clone https://github.com/amelnagdy/guard-skills
git -C guard-skills checkout e749c40f6229

The author documents no install command, so this uses the repository directly. Our verdict covers commit e749c40f6229 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source e749c40f6229

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/amelnagdy/woo-guard/badge.svg)](https://modelsatlas.com/skills/amelnagdy/woo-guard/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

wp-guard✓SAFE

amelnagdy/guard-skills

Review generated or changed WordPress code — plugins, themes, and blocks — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WordPress APIs: add_action/add_filter, shortcodes,…

★ 1.3kGrade B
docs-guard✓SAFE

amelnagdy/guard-skills

Review generated or changed documentation before it ships — READMEs, API references, docstrings, PHPDoc/JSDoc, changelogs, tutorials, and doc sites. Best used reactively after an agent writes or edits docs, after code…

★ 1.3kGrade B
test-guard✓SAFE

amelnagdy/guard-skills

Review generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactors tests, before presenting, committing, or merging them.…

★ 1.3kGrade B
clean-code-guard✓SAFE

amelnagdy/guard-skills

Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes,…

★ 1.3kGrade B
open-code-review✓SAFE

alibaba/open-code-review

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare…

★ 46kGrade B
Build Graph✓SAFE

tirth8205/code-review-graph

Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.

★ 32kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/amelnagdy/woo-guard/badge.svg)](https://modelsatlas.com/skills/amelnagdy/woo-guard/)

Questions about woo-guard

What does the woo-guard skill do?
Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs
Is woo-guard safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can woo-guard access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (e749c40f6229), read on 2026-10-23. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.