AI Blocks › Keep your code secure
Threat modeler
Describe your system. Get threats found with STRIDE, rated by risk, each with a way to reduce it.
Threat modeler 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: advanced · Thinking: high
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
Describe a system and get a list of what could go wrong, ranked by risk, each with a fix. It suits the design stage, when changing a plan costs far less than changing shipped code. The skill walks through the STRIDE method: spoofing, tampering, repudiation, information disclosure, denial of service and elevation of privilege. For each one it asks where your system is exposed, such as logins, data stores or third-party links. It scores likelihood and impact, then suggests controls like multi-factor login, signed requests or stricter logging. It works from your architecture notes or diagrams, and from how sensitive your data is.
You give it
- A description or diagram of your system
- The kind of data it holds
- Outside services it connects to
- Existing security controls (optional)
- Codebase (optional)
You get
- Threats sorted by STRIDE category
- Risk ratings
- Suggested controls for each threat
- A short summary for reviewers
Use it when
- You are designing a new feature that handles personal data.
- You are adding a third-party service and want to know the risk.
- A compliance review is coming and you need documented threats.
- A past incident showed gaps and you want to find the rest.
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.