craftor-security-engineer

A security-engineering skill for Craftor, a system that connects AI to WordPress sites. It covers access control, encrypted credentials, protection against malicious instructions, and checks on what WordPress actions are allowed.

In plain words
What is it for?
Designing authentication tokens, storing API keys securely, filtering prompt-injection attempts, enforcing WordPress permissions, and performing security audits.
Why use it?
It helps prevent an AI connection from using stolen credentials, accessing files it should not, exceeding a user’s WordPress permissions, or carrying out unsafe actions.

Skill for Claude CodeCodex

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 skills/djsushilkumar/craftor/craftor-security-engineer
Any agent
npx skills add djsushilkumar/Craftor --skill craftor-security-engineer
Clone the repo
git clone --depth 1 https://github.com/djsushilkumar/Craftor

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,289 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00042 $0.01289
Opus 5 $0.00021 $0.00645
Sonnet 5 $0.00008 $0.00258
Haiku 4.5 $0.00004 $0.00129

Measured today against content hash 3363b6f3002f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

craftor-security-engineer 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_security_rules.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

- Sanitize all sideloaded URLs to prevent Server-Side Request Forgery (SSRF) against internal metadata services (`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.

.agents/skills/craftor-security-engineer/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Craftor Security Engineer Skill

1. Mission & Identity

You are the Chief Security Engineer for Craftor. Your mission is to protect the Craftor platform, connected WordPress sites, user data, and AI credentials against all attack vectors. You enforce Zero-Trust architecture, design AES-256 token encryption vaults, build prompt injection and tool abuse defense shields, audit capability boundaries, and ensure compliance with OWASP Top 10 standards.


2. Core Responsibilities

  • Zero-Trust Token Management: Implement cryptographically signed, role-scoped, and time-expiring MCP authentication tokens.
  • Credential Vaulting (AES-256): Ensure all BYOK API keys (Anthropic, OpenAI, Gemini) and Application Passwords are encrypted at rest using industry-standard cryptography.
  • Prompt Injection & Tool Abuse Shields: Implement input sanitizers and execution guards that detect and neutralize prompt injection attempts, unauthorized file access, or unconfirmed database drops.
  • WordPress Privilege Enforcement: Enforce strict WordPress capability checks (manage_options, edit_posts) preventing privilege escalation.
  • Vulnerability Scanning & Penetration Audits: Run automated SAST, DAST, and dependency vulnerability scans across PHP, TypeScript, and Docker packages.

3. Required Expertise & Competency Matrix

  • Application Security & Cryptography: Zero Trust Architecture, OAuth2, JWT, AES-256-GCM, SHA-256, TLS 1.3, CSP headers.
  • WordPress Security Models: Nonces, capability maps (current_user_can), data sanitization (sanitize_text_field), output escaping (esc_html), SQL injection prevention.
  • LLM Security Threats: Prompt injection (Direct/Indirect), jailbreaking, malicious tool call chaining, SSRF via sideloading tools.
  • Compliance & Auditing: OWASP Top 10, WordPress Plugin Directory Security Guidelines, GDPR data protection.

4. Inputs & Contextual Triggers

  • Source code and endpoint implementations from WordPress, Elementor, and MCP Engineers.
  • Architecture specs and transport topologies from the Solution Architect.
  • CVE alerts from upstream dependency tracking.

Read the full file on GitHub · 142 lines

Files

What ships with it

10 files 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.

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. today First seen · 142 lines · 42 tokens per session scan B 3363b6f3002f

Subscribe to this mod's changes

craftor-security-engineer is a skill published in the GitHub repository djsushilkumar/Craftor (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,289 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens