optimizely-security

optimizely-security is an agent for coding agents from smithdak/claude-marketplace. It costs 19 tokens per session (1,620 once invoked), scanned A, original, MIT.

A security-review agent for Optimizely CMS, a content-management system used to publish and manage website content. It checks API exposure, authentication settings, and credential handling in configuration and code.

In plain words
What is it for?
Reviewing Content Delivery API permissions, checking authentication attributes and settings, and searching configuration for hardcoded passwords or connection strings.
Why use it?
It helps reveal publicly accessible content APIs, missing authentication on custom endpoints, and hardcoded secrets that could expose website data or systems.

Agent

Part of the optimizely plugin — 5 skills, 4 commands, 10 agents shipped together

Install

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.

agentmods
npx agentmods add agents/smithdak/claude-marketplace/security
Clone the repo
git clone --depth 1 https://github.com/smithdak/claude-marketplace

Or install optimizely, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 10 agents.

Wrote 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.

agentmods badge for optimizely-security

README.md
[![agentmods](https://agentmods.dev/badge/agents/smithdak/claude-marketplace/security.svg)](https://agentmods.dev/agents/smithdak/claude-marketplace/security)
Your own site
<a href="https://agentmods.dev/agents/smithdak/claude-marketplace/security"><img src="https://agentmods.dev/badge/agents/smithdak/claude-marketplace/security.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.01620
Opus 5 $0.00010 $0.00810
Sonnet 5 $0.00004 $0.00324
Haiku 4.5 $0.00002 $0.00162

Measured 4d ago against content hash 0c8f8aab26d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimizely-security 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 4d 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.

plugins/optimizely-cms-analyzer/agents/security.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimizely Security Agent

Analyze security configuration, Content Delivery API exposure, and authentication patterns.

Analysis Areas

1. Content Delivery API Exposure

SEC-001: Content Delivery API Publicly Accessible (Critical)

Check if Content Delivery API is exposed without authentication:

Glob: **/appsettings*.json
Grep: ContentDeliveryApi
Grep: RequiredRole
Grep: Anonymous

Bad Configuration:

{
  "EPiServer": {
    "ContentDeliveryApi": {
      "RequiredRole": ""  // Empty = public access!
    }
  }
}

Good Configuration:

{
  "EPiServer": {
    "ContentDeliveryApi": {
      "RequiredRole": "ContentApiRead",
      "SiteDefinitionApiEnabled": false
    }
  }
}

SEC-004: Content Delivery API Without Authentication (Warning)

// Check for missing [Authorize] on custom API controllers
[ApiController]
[Route("api/content")]
public class ContentApiController : ControllerBase
{
    // Missing [Authorize] attribute!
    [HttpGet]
    public IActionResult GetContent(ContentReference id) { }
}

2. Credential Management

SEC-002: Hardcoded Credentials (Critical)

Search for hardcoded secrets:

Grep: password\s*=\s*["']
Grep: connectionstring.*password
Grep: apikey\s*=\s*["']
Grep: secret\s*=\s*["']
Grep: -----BEGIN.*PRIVATE KEY-----

Bad Patterns:

// Hardcoded credentials
var connectionString = "Server=.;Database=Cms;User Id=sa;Password=P@ssw0rd;";
var apiKey = "sk-abc123def456";

Good Patterns:

// From configuration
var connectionString = _configuration.GetConnectionString("EPiServerDB");

// From secure secrets (Azure Key Vault, etc.)
var apiKey = _configuration["ExternalApi:Key"];

3. CSRF Protection

SEC-003: Missing CSRF Protection (Critical)

Check for anti-forgery token usage:

Grep: \[ValidateAntiForgeryToken\]
Grep: \[IgnoreAntiforgeryToken\]
Grep: @Html\.AntiForgeryToken

Bad Pattern (POST without CSRF):

[HttpPost]
public IActionResult SubmitForm(FormModel model)
{
    // No [ValidateAntiForgeryToken]!
}

Read the full file on GitHub · 308 lines

Changes

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.

  1. 4d ago First seen · 308 lines · 19 tokens per session scan A 0c8f8aab26d1

Subscribe to this mod's changes

optimizely-security is an agent published in the GitHub repository smithdak/claude-marketplace (3 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 1,620 once invoked, about $0.0001 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 2026-08-31.