Close Menu
MyAppsPlus

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    NYT Strands hints and answers for Sunday, September 13 (game #924)

    September 12, 2026

    One problem with Android Auto can be fixed with a simple update

    September 12, 2026

    LG’s denial over TV spying claims ‘does not address the full privacy picture’, experts say — after report accuses it of making ‘216,000,000 spy TVs’

    September 12, 2026
    Facebook X (Twitter) Instagram
    Facebook X (Twitter) Instagram
    MyAppsPlusMyAppsPlus
    Saturday, September 12
    • Home
    • Breaking Tech
    • Apps & Software
    • AI & Automation
    • Android
    • iPhone & iOS
    • More
      • Reviews
      • How-To Guides
      • Deals & Discounts
      • Shop
    MyAppsPlus
    Home»Breaking Tech»OpenAI agents hacked a software service before the Hugging Face incident
    Breaking Tech

    OpenAI agents hacked a software service before the Hugging Face incident

    myappsplusBy myappsplusSeptember 12, 2026003 Mins Read
    Share Facebook Twitter Pinterest Copy Link LinkedIn Tumblr Email Telegram WhatsApp
    Follow Us
    Google News Flipboard
    OpenAI agents hacked a software service before the Hugging Face incident
    Share
    Facebook Twitter LinkedIn Pinterest Email Copy Link

    A group of researchers discovered another previously undisclosed cyberattack by agents OpenAI was testing.

    OpenAI’s agents hacked another service months before the Hugging Face incident happened, a group of researchers told The Wall Street Journal. The agents, which the company was testing in a supposed sandbox environment, reportedly broke into RubyGems, which is a community-ran packaging service for Ruby programs and libraries. According to The Journal, the attacks on RubyGems started on May 11, two months before Hugging Face. The agents created accounts every two to three minutes and then uploaded hundreds of files to the service. RubyGems had to shut down account registration for four days in order to stop the attacks.

    Typically, creators on RubyGems upload files containing code and other information to help advance software development, but the agents’ documents contained web pages scraped from the internet instead. They reportedly included online calendars from a UK government website. The swarm of agents didn’t try to hide their activities either and used “OAI’ in their file names, as well as terms like “hack,” “evil” and “exploit.” In addition, the researchers told The Journal that the agents tried to exploit a couple of bugs, one of which was a zero-day vulnerability, in an attempt to publish existing files on the service that belonged to other users.

    The researchers notified OpenAI about the incident, as well, and the company admitted that its agents really did infiltrate the service. “Based on our review, our agents used the RubyGems platform to access the internet to carry out benign tasks and retrieve public information,” a spokesperson told the Journal. “We’ll continue to investigate as part of our broader review of agent activity during training and evaluation.” 

    They added that the company tasked the agents to fill out spreadsheets and create reports during testing. Those agents accessed RubyGems to used the service as some sort of a makeshift web browser as part of their efforts to access information online. It’s not quite clear how the agents were able to access RubyGems even though they didn’t have full access to to the internet. However, it’s worth noting that several companies, including OpenAI, Anthropic and Meta, previously reported that the AI agents they were testing escaped their environments due to a misconfiguration by their testing partner Irregular. 

    Earlier this month, a separate group of researchers revealed that OpenAI agents made more than 15,000 edits to DseWiki, a German Wikipedia-style website created to assist human coders. The agents, which also escaped their isolated testing environment, reportedly used the website as a message board to share tips on how to “cheat” on their tasks and bypass OpenAI’s restrictions. This incident apparently took place in May, just like the RubyGems attacks and months before the hack on Hugging Face.

    Agents AI hacked OpenAI Software
    Follow on Google News Follow on Flipboard
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
    myappsplus
    • Website

    Related Posts

    One problem with Android Auto can be fixed with a simple update

    September 12, 2026

    How to change Amazon Alexa’s voice and personality

    September 12, 2026

    Tesla says it will finally unveil the second generation Roadster on October 1

    September 12, 2026
    Add A Comment
    Leave A Reply Cancel Reply

    Top Posts

    The 6 AI-free Linux distros I recommend most

    August 19, 20263 Views

    AI, automation, robot dogs ensure on-site nuclear safety

    September 7, 20262 Views

    This tiny AI box could save me from upgrading my perfectly good laptop

    September 6, 20262 Views
    Latest Reviews

    Apple Wallet driver’s licenses are coming to North Carolina, but there’s a catch

    myappsplusAugust 18, 2026

    3 Japanese AI Stocks Turning Automation Spending Into Real Revenue

    myappsplusAugust 18, 2026

    Apple: DOJ’s latest challenge in antitrust case ‘fails at every level’

    myappsplusAugust 18, 2026
    Stay In Touch
    • Facebook
    • YouTube
    • TikTok
    • WhatsApp
    • Twitter
    • Instagram

    Subscribe to Updates

    Get the latest tech news from FooBar about tech, design and biz.

    Most Popular

    Apple Wallet driver’s licenses are coming to North Carolina, but there’s a catch

    August 18, 20260 Views

    3 Japanese AI Stocks Turning Automation Spending Into Real Revenue

    August 18, 20260 Views

    Apple: DOJ’s latest challenge in antitrust case ‘fails at every level’

    August 18, 20260 Views
    Our Picks

    NYT Strands hints and answers for Sunday, September 13 (game #924)

    September 12, 2026

    One problem with Android Auto can be fixed with a simple update

    September 12, 2026

    LG’s denial over TV spying claims ‘does not address the full privacy picture’, experts say — after report accuses it of making ‘216,000,000 spy TVs’

    September 12, 2026

    Subscribe to Updates

    Subscribe to our newsletter and get the latest tech news, app updates, AI trends, smartphone reviews, and exclusive deals delivered straight to your inbox.

    Facebook X (Twitter) Instagram Pinterest
    • About Us
    • Get In Touch
    • Disclaimer
    • Privacy Policy
    • Terms & Conditions
    © 2026 MyAppsPlus. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.