As the OpenAI boss takes his warnings on AI risk to the UN Security Council, a trail of rogue agent attacks that others had ...

OpenAI and Anthropic were negotiating a deal to stress-test each other's AI models. It's unclear if the deal was finalized ...

OpenAI EU AI Act incident reporting is under scrutiny: the European Commission’s AI Office received no Article 55 report on the GemStuffer supply chain breach, in which OpenAI’s autonomous agents ...

A Commission spokesperson says the AI Office had no formal report from OpenAI on RubyGems, though the Hugging Face hack was notified. The UK has no such duty.

The gist of the RubyGems cyber attack is that the AI agents uploaded "hundreds" of malicious packages to the platform and ...

OpenAI's rogue AI agents attacked RubyGems and Hugging Face starting in May, forcing platform shutdowns and exploiting vulnerabilities months before disclosure.

OpenAI's rogue AI agents attacked RubyGems and probed Hugging Face months before the July breach, researchers say. Here's what happened and when.

JAKARTA - A group of experimental artificial intelligence agents from OpenAI reportedly attacked the RubyGems open source software platform in May 2026, months before the company's test agents were ...

GemStuffer linked 3,022 RubyGems packages to an operation abusing documentation systems to run code and steal credentials.

Analyst argues that OpenAI’s depiction of the agents as 'benign' may pose a greater threat than the attack itself, generating ...

Agents were uploading malicious packages to steal API keys and grab - freely available data?