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 MacareuxDigital/concretecms-skills --skill concrete-cms-securitygit clone --depth 1 https://github.com/MacareuxDigital/concretecms-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/macareuxdigital/concretecms-skills/concrete-cms-security)<a href="https://agentmods.dev/skills/macareuxdigital/concretecms-skills/concrete-cms-security"><img src="https://agentmods.dev/badge/skills/macareuxdigital/concretecms-skills/concrete-cms-security/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/macareuxdigital/concretecms-skills/concrete-cms-security"><img src="https://agentmods.dev/badge/skills/macareuxdigital/concretecms-skills/concrete-cms-security.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 | $0.00214 | $0.05126 |
| Opus 5.5 | $0.00086 | $0.02050 |
| Sonnet 5.5 | $0.00043 | $0.01025 |
| Haiku 4.5 | $0.00021 | $0.00513 |
Grade B, and why
concrete-cms-security scanned grade B with 1 finding 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 1mo 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Resolve hostname yourself; reject private ranges (RFC1918, link-local, loopback, IPv6 equivalents, IPv4-mapped IPv6, cloud metadata `169.254.169.254`). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concrete CMS Security
Operational reference for writing or reviewing Concrete CMS PHP. Read top-to-bottom for a new task; jump to Danger signals or Review priorities when triaging an existing PR.
Structure
- Danger signals — grep patterns demanding deeper inspection
- Review priorities — order to inspect a PR, by risk-per-minute
- Critical patterns (C1–C7) — RCE / privesc / auth bypass
- High-frequency patterns (H1–H7) — XSS, CSRF, IDOR, SSRF, etc.
- Pre-flight checklist
- Threat model & history — actors and recurring patterns
Sections 1–5 are the working reference. Section 6 is evidence.
Skip this skill only for documentation/marketing copy, frontend-only changes that add no endpoints, or read-only review without modification.
Danger signals
Stop and apply the linked rule if any of these appear.
RCE class:
| Signal | Rule |
|---|---|
unserialize( |
C1 |
phar://, file://, data://, gopher:// |
C1, H4 |
include $x, require $x (variable path) |
C3 |
move_uploaded_file( |
C2 |
uniqid( used for security/paths |
C2 |
exec, shell_exec, system, passthru, backticks |
— block entirely |
Auth / privilege class:
| Signal | Rule |
|---|---|
$request->request->all(), raw $_POST to update |
C7 |
File::getByID(, Page::getByID(, Event::getByID(, Express*::getByID( |
H3 |
canAccess() before a mutation |
C5 |
== in auth/password/token/guard code |
C6 |
=== true/false on a JSON-decoded field |
C6 |
OAuth callback w/o state, session regen, or uIsActive |
C7 |
| Password/email/2FA change w/o current-password re-verify | C7 |
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.
- 1mo ago First seen · 393 lines · 214 tokens per session scan B 416738a618aa
concrete-cms-security is a skill published in the GitHub repository MacareuxDigital/concretecms-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 214 tokens to every session and 5,126 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other skills, from other repositories
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
laravel-security
Laravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.
integration-fixture
Add a .test integration fixture for one behavior.
Behat BDD Testing
PHP BDD testing with Behat framework using Gherkin feature files, Mink browser extension, context classes, and Symfony integration for behavior-driven acceptance testing.
create-module
Scaffold a new Marko module — a self-contained Composer package with composer.json, namespaced src/, and Pest tests. Use this skill whenever the user asks to create, add, or scaffold a new Marko module or package. Concrete triggers: 'create a module named payment', 'scaffold an acme/blog package', 'add a new module…
phel-lang
Building applications WITH Phel (Lisp that compiles to PHP). Triggers on .phel files, phel-config.php, phel CLI commands (init, run, repl, test, build), or requests to build a Phel app. Skip when working on the Phel compiler itself.