llm-security
Finds security weaknesses in AI applications like prompt injection and data leaks so developers can fix them before launch.
Installation
Paste this into Claude Code, Cursor, or any agent that can run commands.
What this skill does
What it does:
- Tests artificial intelligence chatbots and AI assistants for security problems
- Checks if someone can trick the AI into doing things it should not do
- Tests if the AI can be tricked into revealing secret instructions or accessing tools it should not use
- Looks for ways to poison the AI's memory or knowledge base with false information
- Checks if the AI's output could be dangerous to other computer systems
When to use it:
- You need to test an AI chatbot or assistant for security weaknesses
- You want to see if someone could trick the AI with special prompts or hidden instructions
- You need to check if the AI could accidentally help someone break into systems
- You want to make sure the AI only uses the tools it is supposed to use
- You have permission to test the AI system
The full skill text could not be loaded right now. It installs fine with the command above, or read it at the source.
Mirrored from the author's public source. Install counts from the open skills registry.