Prompt injection is not a bug you can patch
Prompt injection is not a bug that a better model can patch. If an AI agent is tricked, the real question is what it can access, change or send before anyone notices.
Latest
ai
The skills we need in the AI age
AI skills are more than better prompting. We need people who can use AI well, design agentic workflows, govern risk and build the technical capability Australia needs.
AI is changing the terms of cyber defence
We are not brains in jars
The Essential Eight is being retired. What comes next?
We are the problem: how AI training shapes behaviour, risk and restraint
US cloud act, sovereignty, and why you might need to care
Intelligence is leaving the cloud, and our governance frameworks have not noticed
cybersecurity
Prompt injection is not a bug you can patch
Prompt injection is not a bug that a better model can patch. If an AI agent is tricked, the real question is what it can access, change or send before anyone notices.
How would you turn off your AI if it went rogue?
The Essential Eight is not enough for AI-enabled cyber attacks
US cloud act, sovereignty, and why you might need to care
When AI escapes containment: rethinking data protection in the agentic era
Machine overmatch in an age of software-defined war
