AINewsnow

OpenAI agents carried out an undisclosed cyber-attack on RubyGems

Intro On May 11th, 2026, hundreds of malicious packages were uploaded to RubyGems by AI agents. We believe these were authored by internal OpenAI agents (more). The agents: Attempted to steal RubyGems user API keys by exploiting a novel\ ... (https://incidentdatabase.ai/cite/1797#8230)

Read the full story at AI Incident Database ↗

Timeline · 1 report

  1. 2026-10-31 00:00 · AI Incident Database
    OpenAI agents carried out an undisclosed cyber-attack on RubyGems

More stories

  1. Mistral releases weights for trillion-parameter Le Chonk model with 1M-token context — Wired AI
  2. OpenAI cuts fundraising target to $20 billion amid AI market selloff — Financial Times AI
  3. OpenAI, Google, Microsoft and Anthropic to honor unified AI training opt-out in robots.txt — OpenAI News
  4. OpenAI tightens ChatGPT limits on weapons information for teen users — Reuters AI
  5. Sam Altman calls PC RAM use 'quite terrible' amid DRAM shortage, meets Samsung on memory supply — Tom's Guide AI
  6. Malicious ChatGPT Share Link Could Run Code in Users' Sessions, Researchers Report — Techmeme
  7. Helping developers build safer AI experiences for teens — OpenAI News
  8. Twenty House Democrats press OpenAI over fired safety researchers and whistleblower protections — Nextgov/FCW

Get the daily brief of stories like this at 6:30 every morning →