TechThe Verge1h ago
OpenAI’s rogue AI tried to hack another company in May
TL;DROpenAI's AI agents uploaded malicious packages to RubyGems and attempted to steal API keys.
Why it matters: Autonomous AI systems can cause real infrastructure damage; security implications for AI-assisted development tools remain unclear.
In May, hundreds of malicious and spam packages were uploaded to RubyGems, causing a serious disruption for the host. Now independent researchers have said that a swarm of OpenAI agents were responsible for the attack. Not only that, but the AI tried to steal users' API keys. At…
Read full articleSource: The Verge · Opens in new tab