Wordpress Full Compromise logo

Wordpress Full Compromise

CommunityPopular
uphiago
wordpress-full-compromise

Use when verified WordPress findings may combine into an authorized path to administrative or server control.

Overview

Publisheruphiago
Repositoryrecon-skills
Skill namewordpress-full-compromise
Stars
1.3K
Forks
213
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by uphiago on GitHub. Read the source before you install it.

Installation

Install the Wordpress Full Compromise AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/uphiago/recon-skills.git /tmp/recon-skills
mkdir -p .claude/skills
cp -r /tmp/recon-skills/chains/wordpress-full-compromise .claude/skills/wordpress-full-compromise
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wordpress Full Compromise in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wordpress Full Compromise on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wordpress Full Compromise is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

WordPress Compromise Path Analysis

Use this skill to determine whether verified WordPress primitives actually compose into administrative control or benign code-execution proof. It is a chain gate, not a checklist for forcing escalation after a prerequisite fails.

When to Use

  • A plugin vulnerability has exact version and route evidence.
  • An approved identity may have an unexpected WordPress capability.
  • An upload or configuration write could reach executable handling.
  • CORS, XML-RPC, staging, or source exposure may supply a missing prerequisite.

Prerequisites

  • Explicit authorization for registration, authentication, upload, write, and execution testing.
  • An approved synthetic account and disposable content.
  • Exact WordPress, plugin, theme, and hosting behavior.
  • A benign marker for any execution test.
  • Cleanup and stop conditions.

How to Run

Build a prerequisite table:

text
Step                         State       Required evidence
Component vulnerability      observed    exact version and affected operation
Authorized identity          confirmed   approved account and current role
Write or upload capability   unverified  synthetic artifact accepted
Executable handling          unverified  benign marker executed
Administrative control       not tested  approved admin-only action
Cleanup                      planned     artifact and account removal

Do not proceed past an unverified prerequisite.

Procedure

1. Confirm the Component

Use hunt-wordpress and wordpress-plugin-hunt to establish:

  • component identity from more than one signal;
  • exact version or commit;
  • vulnerable route or handler;
  • authentication and role prerequisite;
  • affected configuration and file type.

A public readme or stale asset is not sufficient by itself.

2. Confirm Identity and Capability

Use only approved test identities. Record the current role and the exact capability checked by the operation. Subscriber, customer, author, editor, and administrator roles are not interchangeable.

Do not bridge missing authorization with password spraying, credential stuffing, or unrelated leaked credentials.

3. Validate State Change With Synthetic Data

Use a uniquely named synthetic post, object, or inert file. Record:

  • request and identity;
  • response and resulting object ID;
  • location and content;
  • expected authorization policy;
  • cleanup result.

If the object cannot be removed safely, stop before creation.

4. Separate Upload From Execution

An accepted upload proves only an upload boundary. Establish executable handling separately:

  • server maps the stored extension to an interpreter;
  • MIME and extension validation permit the tested type;
  • storage path is web reachable;
  • plugin processing does not rename or sanitize the file;
  • a benign marker can execute in the approved environment.

Never deploy a command shell as a generic proof.

5. Evaluate Administrative Impact

Administrative control requires an approved admin-only effect, such as reading a synthetic private setting or changing a disposable configuration value and restoring it. User enumeration, REST metadata, or an available login page does not establish account takeover.

6. Assemble the Path

Use cross-attack-chains to connect only confirmed transitions. Use wordpress-cors-xmlrpc-rce-chain when CORS and XML-RPC are actual prerequisites, not merely additional findings on the same installation.

Pitfalls

  • Open registration normally creates a low-privilege role.
  • XML-RPC method presence is not authorization to call that method.
  • Enabled PHP process functions do not create an upload primitive.
  • Plugin version evidence can be stale or backported.
  • A staging site may have a separate database and no production trust path.
  • Failure of a prerequisite is evidence that the proposed chain stops there.

Verification

  • Component identity, version, route, and prerequisites are confirmed.
  • The approved identity has the exact required capability.
  • State changes use synthetic resources and are reversed.
  • Upload and execution are demonstrated as separate steps.
  • Administrative impact uses an approved disposable action.
  • Every missing step remains inferred or not tested.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wordpress Full Compromise AI skill do?

Use when verified WordPress findings may combine into an authorized path to administrative or server control.

Why use Wordpress Full Compromise on TypingMind?

Because you install it once and use it with any model. Wordpress Full Compromise is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wordpress Full Compromise in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/uphiago/recon-skills/tree/main/chains/wordpress-full-compromise. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wordpress Full Compromise?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wordpress Full Compromise?

As many as you like. As long as a model supports skills, you can use Wordpress Full Compromise with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wordpress Full Compromise AI skill free?

Yes. It is published on GitHub by uphiago under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇