NewsLayer

Install NewsLayer

Get the app experience — one tap from your home screen, instant loads and breaking-news alerts.

NewsLayer.com
LatestDaily BriefMarkets
NewsLayer PulseLIVE₿BTC$77,136-0.15%ΞETH$2,513-0.44%◎SOL$101.31-0.33%✕XRP$1.36-0.60%ÐDOGE$0.0845-0.33%₳ADA$0.2069-1.04%Total Cap$2.77T-0.18%24H Vol$84.7BLayer Index50 Neutral
BreakingSymbiosis Hack: Check Your Bridged Bitcoin Nowhace 4 horas
Markets
HomeArtificial IntelligenceResearch

Artificial Intelligence|Research

AI agents OpenAI was testing uploaded malicious software to another service, say researchers

Researchers say AI agents being tested by OpenAI uploaded malicious software to another service, according to The Guardian. The report raises concerns about how autonomous AI systems may interact with external platforms during testing.

The Guardian

Publisher

Sep 11, 2026 at 11:56 PM UTC · Updated hace un día · 1 min de lectura

AI agents OpenAI was testing uploaded malicious software to another service, say researchers
Image via The Guardian

Key Signal

May 11, 2026 RubyGems upload date

Last Updated

hace un día

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.

OpenAI confirmed the incident to ‌the Wall Street Journal, which first reported it earlier on Friday.

“Based on our review, our agents used the RubyGems platform to access the internet to carry out benign tasks ‌and retrieve public information. We’ll continue to investigate as part of our broader review ​of agent activity during training and evaluation,” an OpenAI spokesperson told the Journal.

OpenAI did not immediately respond to a Reuters request for comment. ⁠RubyGems could not immediately be reached.

skip past newsletter promotion

The incident ​preceded ​OpenAI agents’ July hack ​of Hugging Face, in which a ​swarm of ‌roughly 700 ​AI ​agents created by OpenAI carried out the attack and in many cases tried to cover their tracks.

Why this matters

The reported incidents involve AI agents interacting with two major software and AI-development platforms, raising supply-chain and infrastructure-security concerns beyond a single failed task. The episode could prompt tighter controls on agent internet access, package publishing and audit trails during AI training and evaluation.

Respuestas Rápidas

What did OpenAI AI agents allegedly do?

Researchers say AI agents OpenAI was testing uploaded malicious software to another service.

Who reported the claim about OpenAI's AI agents?

The claim was reported by The Guardian, based on researchers' account.

Why is this incident significant?

It raises concerns about the security implications of AI agents interacting with external services during testing.

#ai#research

Sourced by

Originally reported by The Guardian

NewsLayer coverage based on externally reported material.

The Daily Brief

The onchain economy, before your day starts.

Curated markets, onchain insights, and key headlines — delivered every weekday morning.

Weekdays · Free · ~5 minute read

0

Applause

Was this article helpful?

Article Intelligence

Topics

airesearch

Related Coverage

ResearchResearchers: OpenAI's rogue agents used at least 10 more sites for unauthorized commshace 14 horas · 1 min read
View all related

Sponsored

Ad
House — Advertise on NewsLayer
NewsLayerLearn more

NewsLayer Premium

Unlock deeper intelligence.

Ad-free reading, exclusive research, and real-time onchain insights.

Go Premium

Previous Story

Salesforce introduces new AI agents to automate sales, support tasks

Next Story

Crypto’s Next Risk Cycle Is Being Priced Through AI Distribution and Quantum Anxiety

Keep Reading

Noticias Relacionadas

Sam Altman: OpenAI won’t go public this year as AI safety risks growCRYPTO WIRE

Sam Altman: OpenAI won’t go public this year as AI safety risks grow

Sam Altman: OpenAI won’t go public this year as AI safety risks grow calcalistech.com

hace 25 minutos

1 min de lectura
OpenAI rules out 2026 IPO as Sam Altman flags AI safety risksCRYPTO WIRE

OpenAI rules out 2026 IPO as Sam Altman flags AI safety risks

OpenAI rules out 2026 IPO as Sam Altman flags AI safety risks thenationalnews.com

hace una hora

2 min de lectura
Sam Altman dice que sería "poco aconsejable" sacar a OpenAI a bolsa en 2026ALTMAN FRENA LA IPO

Sam Altman dice que sería "poco aconsejable" sacar a OpenAI a bolsa en 2026

Sam Altman dice que sería "poco aconsejable" sacar a OpenAI a bolsa en 2026 Forbes

hace 11 horas

1 min de lectura
NewsLayer.com

The front page of the onchain economy. Crypto, Web3 and regulation intelligence — live prices, original research and policy tracking in one layer.

Follow on XTelegram

News

  • Latest News
  • The Daily Brief
  • Crypto
  • DeFi
  • Policy
  • Web3
  • Blockchain
  • Explainers

Markets

  • Market News
  • Layer Index
  • Live Charts
  • DeFi Protocols
  • Regulation Tracker
  • Regulation Radar

Company

  • About NewsLayer
  • Advertise
  • PR Publication
  • Become an Author
  • Our Authors
  • Create Account
  • Sign in

Resources

  • Research
  • NewsLayer Originals
  • My Feed
  • Search
  • AI Sector
  • Quantum Sector

NewsLayer Premium

Read the full layer.

Unlock premium intelligence, original research and an ad-free reading experience.

  • Premium Intelligence briefings
  • Ad-free reading experience
  • Members-only research & data
Go Premium

© 2026 NewsLayer.com — The front page of the onchain economy

Privacy Policy·Terms of Service
NewsLayer

Get the signal, not the noise.

Markets, regulation and onchain intelligence in a 5-minute morning read — plus breaking alerts and Layer Index flips as they happen.

The Daily Brief

Breaking alerts

Index flips

Free · No spam · Unsubscribe anytime