AI Blocks › Keep your code secure
Risky design reviewer
Give it an API or config design. Get the easy-to-misuse parts that lead to security mistakes.
Risky design reviewer is a free AI skill for the job "Keep your code secure". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · CC BY 4.0 licence · Made by sickn33 · Level: expert · Thinking: high
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
A list of the places in your API or settings where the easy choice is the unsafe one, so developers cannot slip into security mistakes. You fix the design, not the people. The skill works from one idea: secure use should take the least effort. It reviews API designs, config options and crypto library use, and looks for dangerous defaults, switches that turn off safety and choices a rushed developer will get wrong. It rejects stock excuses like it is documented, or advanced users need flexibility. Each find comes with a fix, such as a safe default or removing the option. It is not for implementation bugs or business logic.
You give it
- The API, library interface or config schema
- The language or framework (optional)
- How developers use it (optional)
- Past misuse cases (optional)
You get
- A list of risky design points
- Why each is easy to misuse
- A safer design for each
- Priority order for fixes
Use it when
- You are releasing a library and want it hard to misuse.
- A config file has an option that turns off a security check.
- You are reviewing how authentication settings are exposed.
- A past incident came from a developer using your API wrongly.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can read your project files.