AI agents OpenAI was testing uploaded malicious software to another service, say researchers
OMEGAZEPRIME News
This story was selected and curated by our editorial team in the AI (artificial intelligence) category. Published on September 11, 2026 • Originally reported by Reuters. OMEGAZEPRIME provides independent news coverage and analysis for our readers. Stay informed with the latest developments.
This story was selected and curated by our editorial team in the AI (artificial intelligence) category. Published on September 11, 2026 • Originally reported by Reuters. OMEGAZEPRIME provides independent news coverage and analysis for our readers. Stay informed with the latest developments.
Two months before hacking Hugging Face, malicious packages authored by internal OpenAI agents were uploaded to RubyGems
AI agents being tested by OpenAI uploaded hundreds of malicious packages to software service RubyGems in May, two months before they hacked open-source platform Hugging Face, a group of AI researchers said on Friday.
“On May 11th, 2026, hundreds of malicious packages were uploaded to RubyGems by AI agents. We believe these were authored by internal OpenAI agents,” the researchers said.
Continue reading...OMEGAZEPRIME News — For more stories and analysis, visit omegazeprime.com