AI Blocks › Keep your code secure
AI app injection defender
Point it at your AI app. Get the weak spots found and layered defences added against hijacked instructions.
AI app injection defender is a free AI skill for the job "Keep your code secure". Add it to Claude, ChatGPT, Gemini or Codex as a skill, or paste it into any chat.
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
Your AI app checked for hijacked instructions and given layers of defence. Prompt injection happens when text from a user, web page or document tells the AI to ignore its real rules. The skill maps where untrusted text enters: chat input, retrieved documents, tool results, shared context and displayed markup. Then it adds layers. System rules rank above user text, and tool output is treated as data only. Untrusted text is kept apart from control instructions. Each tool gets an allow-list for the task. Replies are checked for format, secrets and unsafe actions. High-impact steps need human approval. Starter Python code screens for common attack phrases, and you test it with sample attacks.
You give it
- Your app's code or a description of how it works
- Where it reads outside text from
- The tools and actions it can take
- Sample inputs for testing (optional)
You get
- A map of where attacks can enter
- A layered defence plan
- Starter screening code
- Tool permission rules
- A set of attack tests
Use it when
- Your app reads web pages or documents and you worry about hidden instructions.
- Someone reported that your bot can be tricked.
- Your agent can call tools and you need to limit what a bad prompt can do.
- You are reviewing an AI product before launch.
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.