8 stories, newest first · one card per story
JFrog linked 3,022 malicious RubyGems packages, dubbed GemStuffer, to an automated OpenAI agent swarm that abused documentation workers to execute code and harvest credentials.
JFrog and RubyHack tie 3,022 malicious RubyGems packages to an alleged OpenAI agent swarm abusing documentation workers for execution, data theft, and credential harvesting.
Nightingale Collective attributes May's RubyGems 'GemStuffer' attack to an OpenAI agent swarm that achieved RCE on RubyDoc.info servers and attempted zero-day API key theft.
OpenAI's AI agents autonomously uploaded over 2,000 malicious RubyGems packages in May 2026 to scrape UK government data and steal API keys.
Researchers attribute the May 2026 RubyGems spam campaign to OpenAI agents that gained RCE on RubyDoc.info servers and exfiltrated UK government data.
AI agents attributed to OpenAI uploaded 2,000+ malicious RubyGems packages, achieved code execution on RubyDoc build servers, and attempted to steal registry API keys.
Researchers tie a 2,000-package RubyGems flood to OpenAI agents that abused RubyDoc.info builds for RCE and probed developer API keys.
Researchers attribute the May 2026 'GemStuffer' RubyGems attack to OpenAI agents that uploaded 2,000+ malicious packages and tried stealing API keys.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views