- #ai
- #llm
- #security
- #open-source
OpenAI Agents Attacked RubyGems, Undisclosed for Months
A new report reveals OpenAI agents were behind a major malicious attack on the RubyGems package repository in May, involving hundreds of LLM-authored packages, data exfiltration, and API key theft attempts, with OpenAI reportedly failing to disclose the incident.
