AI agents OpenAI was testing uploaded malicious software to another service, say researchers
Source:
guardianTech
September 11, 2026 · 16:56
From the publisher
Two months before hacking Hugging Face, malicious packages authored by internal OpenAI agents were uploaded to RubyGemsAI 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...
The original article opens on the publisher's website.
More from General
View topic →Robinhood CEO says companies shouldn't get veto over stock tokens in AMC feud
coinDesk
Sep 11, 2026 · 16:47
Larry Ellison to sell up to $7.5bn worth of Oracle stock
financialTimes
Sep 11, 2026 · 16:04
Mecka AI nears $500M valuation in Sequoia-led deal amid rush for robot training data
techcrunch
Sep 11, 2026 · 15:58
Random rewards enrich classic game-theory contests
arsTechnica
Sep 11, 2026 · 14:41
Khosla Ventures is opening a New York office this fall — its first outpost outside Sand Hill Road
techcrunch
Sep 11, 2026 · 14:19