AI Blocks › Keep your code secure
Security-focused change reviewer
Give it a pull request or commit. Get a security review of only what changed, with risks ranked.
Security-focused change 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: advanced · Thinking: high
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
A security review of just what changed in a pull request, commit range or diff, with each risk backed by line numbers, history and a realistic attack story. It scales to the size of the codebase: deep reading for small ones, focused for mid-size, and only critical paths for large ones. Changes are rated by risk, not size, since a two-line edit to sign-in code can matter more than a big refactor. High risk covers auth, crypto, outside calls and removed checks. It works in phases: triage, code analysis, test coverage, blast radius, deep context and an adversarial pass. It always writes a markdown report and states what it could not cover.
You give it
- A pull request, commit range or diff
- Access to the repository and its history
- Notes on what the change is meant to do (optional)
You get
- Findings with line references
- Attack scenarios for each risk
- A blast radius estimate
- Test coverage gaps
- A markdown report with confidence level
Use it when
- A pull request touches login or permissions and needs a security look.
- A small change removed a validation check and you want it assessed.
- You want a written report you can attach to a review.
- Your team reviews many changes and needs risk ranked first.
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 run code and read your project files.