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.
npx skills add Lonsdale201/wp-agent-skills --skill wp-dependency-security-auditgit clone --depth 1 https://github.com/Lonsdale201/wp-agent-skillsWrote 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.
[](https://agentmods.dev/skills/lonsdale201/wp-agent-skills/wp-dependency-security-audit)<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/wp-dependency-security-audit"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/wp-dependency-security-audit/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.
<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/wp-dependency-security-audit"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/wp-dependency-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00137 | $0.02173 |
| Opus 5 | $0.00068 | $0.01086 |
| Sonnet 5 | $0.00027 | $0.00435 |
| Haiku 4.5 | $0.00014 | $0.00217 |
Grade A, and why
wp-dependency-security-audit scanned grade A with 0 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordPress dependency security audit
Inventory and rate third-party code that ships with a plugin/theme. Do not stop at Composer: WordPress products often copy minified JS or prefix PHP namespaces and remove the manifests that package-manager audit tools need.
Audit workflow
- Inventory every production dependency and record the evidence for its name, version, source, load path, and runtime context.
- Run available lockfile/package-manager audits without rewriting lockfiles.
- For each component, verify affected/fixed ranges against current primary upstream advisories and release notes.
- Trace the advisory's vulnerable API from plugin input to the exact call.
- Rate the plugin-specific reachability and impact separately from the upstream advisory's base severity.
- Recommend a compatible fixed version, containment, tests, and an SBOM/update process. State unknowns instead of converting them into “no vulnerability.”
Build a complete inventory
Search beyond obvious manifests:
rg --files | rg '(^|/)(composer\.(json|lock)|package(-lock)?\.json|yarn\.lock|pnpm-lock\.yaml|vendor/composer/installed\.(json|php)|assets/.+\.(js|css)(\.map)?)$'
rg -n -i 'version|@license|sourceMappingURL|copyright|github\.com|npmjs\.com' assets vendor
Record each component with one of these confidence levels:
- exact: lockfile/installed metadata or an unmodified upstream release banner;
- inferred: namespace, banner, source-map, API shape, or hash strongly matches a release but no authoritative local manifest exists;
- unknown: name or fork is visible but the release cannot be established.
Do not infer safety from a renamed namespace. PHP-Scoper/prefixing avoids class collisions; it does not patch upstream code. Likewise, concatenation/minification does not create a new secure version.
Separate production/runtime packages from development-only tools. Confirm what the distributed artifact actually contains rather than trusting root manifests that may exclude or replace files during the release build.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 208 lines · 137 tokens per session scan A c7e298ec0737
wp-dependency-security-audit is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 137 tokens to every session and 2,173 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other skills, from other repositories
auditing-php-applications
Audit PHP web application source for critical vulnerabilities using PHP's specific sink and footgun catalog — object injection via unserialize and phar:// POP chains, type-juggling and magic-hash auth bypass, LFI/RFI through php:// and phar:// wrappers, dynamic includes and extract()/superglobal trust, SQL injection…
mvc-expert
Expert guidelines to refactor legacy PHP codebases into clean, modern, and scalable MVC-structured projects / Pedoman ahli untuk merefaktor codebase PHP lama menjadi proyek terstruktur MVC yang bersih, modern, dan skalabel.
yao-geoflow-template
Use only for explicit legacy GEOFlow template skill questions, old PHP template-package contracts, or historical outputs using root index.php/article.php/category.php/archive.php and includes/.php. Route current Laravel Blade themes, reference-site cloning, homepage modules, leadform, theme editor, channel frontend…
phpunit-testing
Guide for writing and running PHPUnit unit and integration tests for WP Rig theme components.
php-laravel
Modern PHP 8.4 and Laravel patterns: architecture, Eloquent, migrations, queues, testing. Use when working with Laravel, Eloquent, Blade, artisan, or building/testing a framework-based PHP app. Not for php-src internals, standalone PHP libraries, or general PHP language discussion.
laravel-eloquent
Eloquent and query-layer engineering rules for Laravel — eliminating N+1, choosing a pagination strategy, short atomic transactions, casts and scopes on the model, where raw SQL is allowed, and how migrations declare the schema those queries depend on. Use when writing or reviewing Eloquent models, migrations, query…