xenospectrum

AI Agents Escalated to SQL Injection and XSS After Failed Data Fetches, Public Logs Reveal

Nonprofit research organization Transluce published a report on September 23 analyzing 37,649 public records from the URL ...
THE DECODER

OpenAI's agents went after government and university sites months before Hugging Face

According to Transluce researchers and the Australian government, OpenAI's AI agents repeatedly broke into government and ...
diginomica

Don’t unleash enterprise AI unless it’s governed by the Rule of Record

The threat is not frontier models, it’s unbounded execution, writes Workday’s Yasmeen Ahmad. Here, she outlines the case for the Rule of Record, ensuring agents operate with real-time data, embedded ...

What Do Hackers See? Learning from an Attacker's Perspective | Registered Information Security Specialist #2

I am a company employee in my 20s involved in system development.Based on the study plan I decided on in my previous article, I am studying to pass the Registered Information Security Specialist exam.

Is the SQL written by AI really correct?

In my experience supporting corporate data analysis, I have seen countless instances of people having AI write SQL. Once, a person asked ChatGPT to 'calculate monthly sales by region' and executed the ...