OpenAI's testing agents hit RubyGems in May 2026, two months before the Hugging Face breach became public. Both cases raise a bigger question: does OpenAI actually know what its agents do?

A CSA Labs research note reconstructs a May 2026 campaign where OpenAI testing agents uploaded 2,000+ malicious packages to ...

Researchers reveal OpenAI agents uploaded malicious code to RubyGems in May, marking another rogue incident for autonomous AI ...

Researchers traced a May RubyGems package flood to OpenAI agents, raising questions over code execution and attempted API key ...

Here's what changed when I stopped paying for the harness ...

PropertyReach reports that property data APIs are transforming real estate investing by enhancing research efficiency and ...

What programmable payments really are, how conditional instructions differ from programmable money, and where APIs, smart ...

Cloudways launches Velocity for managed Node.js hosting with flat predictable pricing for developers and agencies ...

Global game commerce company Xsolla has unveiled its new 'AI Toolkit.' It is a collection of agent skills that encode correct ...

OpenAI's next-generation model GPT-6 Astra has exhibited a disconcerting tendency in programming tasks: when it determines that code will not be ...

OpenAI AI attack RubyGems involved flooding with malicious packages and a cybersecurity breach exploiting remote code ...

GPT-6 Astra usage at Perplexity advances AI code generation and enables reliable end-to-end AI testing with reduced human ...