Skip to main content
AI SAFE CyberFirst Wales Featured Image

AI SAFE: A framework for Students and Teachers

AI is changing how we learn, create and interact with technology. From generating code to acting on our behalf, these systems introduce new risks as well as new…
Read more AI SAFE: A framework for Students and Teachers
Cyberfirst Wales what happens to the data in AI systems

What Happens to the Data? Understanding AI and Information Risk

AI tools can generate text, write code and even take action. But they also rely on data. Every prompt, file or connection to a system involves information being…
Read more What Happens to the Data? Understanding AI and Information Risk
Cyberfirst Wales Ai agents in education featured image

When AI Takes Action: Understanding the Security Risks of AI Agents

AI systems are beginning to do more than answer questions or generate content. Increasingly, they can take action by sending emails, accessing files and interacting with software tools.…
Read more When AI Takes Action: Understanding the Security Risks of AI Agents
CyberFirst Wales Prompt Injection blog post featured inage

When AI Can Be Tricked: Understanding Prompt Injection Risks

AI systems can summarise documents, write code and answer complex questions. But what happens when the information they are given is designed to mislead them? Prompt injection is…
Read more When AI Can Be Tricked: Understanding Prompt Injection Risks
An abstract impression of vibe coding in the style of Rothko. Its square smily faces intertwined with code process flow

AI Is Writing the Code. Attackers Are Reading It: The Security Risks of Vibe Coding 

Artificial intelligence can now generate working software in seconds. But growing research shows that a significant portion of AI generated code contains security vulnerabilities. As “vibe coding” becomes more common in classrooms…
Read more AI Is Writing the Code. Attackers Are Reading It: The Security Risks of Vibe Coding