Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

Prompt injection works because language models struggle to tell the difference between trusted instructions and untrusted user content. Unlike SQL injection or cross site scripting, there is no clean deterministic defence, which leaves code, libraries and AI workflows open to manipulation at multiple points.

What happens when your organisation adopts AI faster than your security strategy can keep up? Welcome to Razorwire, the podcast where we share our take on the world of cybersecurity with direct, practical advice for professionals and business owners alike. I’m Jim and in this episode, I’m joined by Martin Voelk, penetration tester and AI red teamer, and Jonathan Care, lead analyst covering the intersection of AI, cybersecurity and identity.

AI agents with browser access can be manipulated into downloading and running malware disguised as a harmless support tool. It is social engineering for machines, where prompt injection turns an innocent browsing task into a full system compromise without any classic CVE in sight.

Regular pen tests and occasional vulnerability scans no longer match the speed of AI driven development and daily changes in modern systems. The real risk now sits in fast moving exposures, chained attacks and agentic behaviour that traditional CVE focused thinking was never built to handle.

This episode explores why CTEM matters in a world of vibe coding, AI agents and rapidly expanding attack surfaces. It covers prompt injection, hidden threats, deepfakes, weak governance and the growing fear that businesses are deploying AI far faster than security teams can understand or control it.

Cybercrime is up around 300% and AI is the reason. Cybercriminals are using large language models with no guardrails to accelerate phishing attacks, deepfakes, social engineering and malicious code generation. Information security professionals need to understand how AI is changing the threat landscape before it's too late.

The word hacker did not start as an insult, it described people pushing technology beyond what it was designed to do. The clip reframes hacking as curiosity, experimentation and technical creativity, while showing how the meaning only became darker when malicious intent entered the picture.

A single film turned teenage curiosity into a lifelong career in information security, long before most people had access to computers at all. War Games made hacking look technical, dangerous and fascinating, and that early obsession became the start of a serious path into InfoSec.

This episode explores why information security needs more wisdom, less noise and fewer empty promises about being “GDPR compliant.” It covers slowing down, valuing data properly, cutting through bad advice and why InfoSec professionals need to own their place as integral voices in modern organisations.  ⸻ For more information about us or if you have any questions you would like us to discuss email podcast@razorthorn.com. We give our clients a personalised, integrated approach to information security, driven by our belief in quality and discretion..

Cybersecurity professionals and CISO roles are under threat. Not from hackers - from AI. Information security leadership, risk management and security strategy are being marketed as something artificial intelligence can now handle. But there's a serious problem with that assumption.