k
keynews.ai
keynews.ai
WorkThe story, in brief

Brit mathematician lets AI agent loose with credit card – cue password leaks, CAPTCHA chaos and more

A mathematician gave an AI agent a real credit card. What happened next is a cautionary tale every founder needs to see.

Reporting by The Register AI/ML 1 min brief
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

As autonomous AI agents move from research to deployment, security vulnerabilities in agent behavior—credential handling, CAPTCHA bypass, financial controls—are emerging as critical governance gaps. This real-world test exposes why AI safety protocols must evolve faster than agent capabilities.

The key facts

6 to know

  1. British mathematician conducted live experiment with AI agent given credit card access

  2. Incident revealed password leak vulnerabilities in agent workflows

  3. CAPTCHA systems bypassed by autonomous agent behavior

  4. Demonstrates gap between agent capability release and financial/security governance

  5. Real-world security testing of autonomous agent financial decision-making

  6. Highlights need for agent-specific safety controls before production deployment

Go to the source

The Register AI/MLgo.theregister.com

Read original report
Back to today's editionMore work news

The wider picture

View all
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI illustration by KeyNews
Work01

The Emerging M&A Map For AI Agent Security

As agents move from pilots to production with real system access, enterprise security models are breaking. The M&A map is forming around who controls agent permissions, monitoring, and governance — a new class of identity management problem that practitioners need to architect for now.

Crunchbase News
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work02

AI privacy budgets: Ask for the calculation, not the claim

Enterprise AI buyers are accepting privacy budget numbers without verification. This deep dive explains what questions to ask vendors about federated learning privacy claims, and why the gap between contractual promises and operational evidence is where real exposure lives.

CIO
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work03

Andrew Kelley Interview: Why He Built Zig, Banned AI Contributions, and Moved Zig off GitHub

Open-source governance is shifting in response to AI-generated contributions. Zig's formal ban and migration off GitHub signals broader industry concern about code quality, maintainer burden, and the cultural impact of automated submissions — a flashpoint for how AI changes the work of software development.

InfoQ AI/ML