The VibeSec Reckoning

The VibeSec Reckoning

Why prompting your AI to “be secure” is not enough, and what<br>actually is

“Vibe coding” - the practice of non-technical citizen builders using<br>generative AI tools to rapidly develop applications, this has significantly accelerated<br>software prototyping. However, because AI agents naturally prioritise the path of<br>least resistance, they frequently recommend insecure configurations, creating systemic<br>security exposure across industries. To combat this we need to write a<br>security context file to guide the AI, be cautious with AI permission<br>requests, create a daily security intelligence feed, and provide builders with<br>a secure-by-default harness and templates.

27 May 2026

Gautam Koul

Gautam is Head of AI applications, Global Marketing at Thoughtworks.<br>He leads AI platform initiatives and applied AI engineering teams focused on building and scaling production-ready,<br>token-efficient GenAI applications across the Google ecosystem.

Lucian Moss

Lucian is an AI Engineer in Global Marketing at Thoughtworks,<br>specialising in Retrieval Augmented Generation and agentic systems.

Neil Drew-Lopez

Neil is an AI Engineer in Global Marketing at Thoughtworks, specialising in data engineering,<br>multi-agent systems, and research into new AI capabilities.

Daberechi Ruth Edeokoh

Ruth is an AI engineer in Global Marketing at Thoughtworks who builds intelligent systems and AI agents that turn complex data into practical insights and scalable,<br>real-world solutions.

Contents

What we learned the hard way

The numbers behind the risk

The real problem: prompts are not enough

Why business functions need to pay attention

Short-term habits

Medium-term solutions

The security context file in practice

The security intelligence feed in practice

Long-term organisational changes

Conclusion: Scaling Beyond the Prototype

Vibe coding is enabling non-technical users (or as we call them, citizen<br>builders) to build applications with AI that they simply could not have<br>built before. When our AI applications team in Global Marketing at<br>Thoughtworks was asked to scale a vibe coded prototype built by one of our<br>citizen builders in global marketing, we discovered serious cracks that<br>prevent vibe coded applications from going into production safely.

Speed without guardrails is a risk no team can afford to ignore. What<br>follows is the story of what we found, what it means for teams building with<br>AI, and the steps we are taking to make sure every workflow, prototype, and<br>app we ship is one we can stand behind.

What we learned the hard way

The AI applications team within Global Marketing was asked to scale a video<br>assembly prototype built with Gemini, Replit AI and Claude AI to create<br>on-brand videos to be used across our 10,000 employees. The team ran into two<br>moments that stopped work cold. In both cases, the AI suggested a path with<br>serious security implications. In both cases, it took a human asking the right<br>question to catch it.

Security risk # 1

Public storage access

The AI recommended making the storage<br>bucket public, or setting cloud file storage to “anyone with the link.” When<br>challenged, it justified this by saying every company does it. Only a firm<br>rejection prompted a secure alternative.

This could have leaked sensitive<br>unreleased brand assets and audience data to the public internet.

Security risk # 2

Excessive token permissions

A service account was assigned the Access<br>Token Creator role, granting it the ability to create short-lived tokens and<br>access databases and other resources far beyond what the task required. The team<br>caught this before running the code.

This would have allowed a compromised<br>service account to move laterally through an entire cloud workspace.

The key insight here is that AI tools often suggest the path of least<br>resistance. That path is not always the secure one. Human judgment remains<br>essential, but it should not be the only control. The goal is to give<br>agents technical security rules as context from the first prompt, then<br>validate their output through deterministic checks in the development<br>workflow so insecure code, permissions, secrets, or infrastructure cannot<br>pass unnoticed.

The numbers behind the risk

44%

Rise in attacks exploiting application vulnerabilities, year on year

1 in 5

Enterprise breaches now caused by AI-generated code

50%

Organisations with no sensitive data policies for AI

25%

AI-generated code with confirmed vulnerabilities

These incidents are not isolated. Research published in 2026 confirms that<br>AI-assisted coding at speed creates systemic security exposure. The same risks<br>we encountered are playing out across the industry right now.

FindingStatSource

AI-generated code with confirmed vulnerabilities25%AppSec Santa, 2026

Rise in attacks exploiting application vulnerabilities, year on year44%SQ Magazine AI Coding Security Statistics, 2026

Codebases with high or critical severity vulnerabilities78%Black Duck OSSRA...