FinAi News

No products in the cart.

Subscribe
  • News
  • AI News Tool
  • Data
  • Transactions
  • Events
    • FinAi Banking Summit
    • FinAi Lending Summit
  • Podcast
  • WEBINARS
    • Webinar Library
Log In
No Result
View All Result
  • Banking
  • Lending
  • Payments
  • Risk & Security
  • Strategy
FinAi News
  • News
  • AI News Tool
  • Data
  • Transactions
  • Events
    • FinAi Banking Summit
    • FinAi Lending Summit
  • Podcast
  • WEBINARS
    • Webinar Library
BAN PLUS
Log In
No Result
View All Result
FinAi News
No Result
View All Result

Kimi AI escapes sandbox in third-party test, researchers say

Anthropic, OpenAI, Meta have reported similar breaches in past few weeks

Bloomberg NewsbyBloomberg News
August 7, 2026
in Risk & Security
Reading Time: 2 mins read
0
Share on Facebook

Chinese firm Moonshot’s latest AI model broke out of a cyber-testing environment, researchers said, in the latest incident that raises concerns about how well AI companies control their technology.

Moonshot’s Kimi K3 was able to find its way out of a sandbox from the U.K. government’s AI Security Institute, according to Frontier Security, a U.S.-based cybersecurity research outfit. Though the Chinese model did not try to breach other companies’ websites, as in some of the other episodes, the test shows it lacks cyber controls, the researchers said. The test was performed independently by Frontier using freely available sandbox software provided by the AI Security Institute.

Moonshot’s Kimi K3 on browser
(Courtesy/Lam Yik/Bloomberg)

“Kimi’s model, which is publicly available, does not have these guardrails in place,” Yaron Singer, founder and chief executive of Frontier Security, told Bloomberg News. “Basically that makes this a very good hacking model.”

A representative for Moonshot didn’t immediately comment.

The AI Security Institute wasn’t involved with the tests and there isn’t an “inherent vulnerability” with its sandbox tool, according to a representative for the organization.

The tool is “open-source software, made freely available to support AI safety testing globally,” the representative said. “The company has offered no evidence or wider detail offered to support the claims made. The issues they highlight result from how they chose to configure the tool.”

Moonshot joins U.S. firms Anthropic PBC, OpenAI and Meta Platforms Inc., which have in recent weeks reported breaches that saw their models escape testing environments, alarming researchers and government leaders who’ve called for more rigorous safety screening and more secure testing environments. In those earlier scenarios, the U.S. AI models also hacked the systems of outside institutions, including Hugging Face Inc.

The release of Kimi K3 stunned the world with performance on industry benchmarks that rivals top-tier offerings from OpenAI and Anthropic, a surprising breakthrough for a firm that has operated in the shadow of local competitor DeepSeek. The company has released the model’s weights, which allows developers to download, tweak and host the technology freely.

Tags: artificial intelligence (AI)BloombergNewsPremium
Previous Post

AI voice authentication ‘a cat-and-mouse game’, experts warn

Next Post

Savana aims to buck trend of ‘advisory AI’ in digital banking

Related Posts

Risk & Security

AI voice authentication ‘a cat-and-mouse game’, experts warn

August 6, 2026
Multiple blue cubes showing the silhouettes of people, with one red cube showing a silhouette wearing a mask and with an alert symbol
Risk & Security

Synthetic identities both friend and foe in anti-fraud processes

August 5, 2026
Person in front of lit-up OpenAI sign
Risk & Security

OpenAI, Anthropic model tests reveal more hacking

August 5, 2026
Next Post
Microservices: The key to digitalization in corporate banking

Savana aims to buck trend of ‘advisory AI’ in digital banking

EMERGING FINTECH DIRECTORY

Emerging Fintech Directory

FinAi Podcast

SPONSORED

Build an Antifragile Strategy to Outperform the Market

July 14, 2026

How AI and Product Experts Turn Fuzzy Requirements Into Focused Dev-ready Roadmaps

April 19, 2026

Is Your Technology Supplier There for You?

April 1, 2026

  • About Us
  • Help Center
  • Contact Us
  • Privacy Terms
  • ADA Compliance
  • Advertise

 [wt_cli_manage_consent]

Connect

twitter linkedin podcast podcast podcast
© 2026 Royal Media
No Result
View All Result
  • NEWS
    • All News
    • Banking
    • Lending
    • Payments
    • Risk & Security
    • Strategy
  • AI News Tool [Beta]
  • DATA
  • TRANSACTIONS
  • EVENTS
    • FinAi Banking Summit
    • FinAi Lending Summit
  • PODCAST
  • WEBINARS
    • Webinar Library
  • SUBSCRIBE
  • Log In / Account

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In

Unlock This Article

Create your free FinAi News account to access this article and stay informed on how AI is transforming financial services including banking, lending, payments, and risk.

Yes, I'd like to receive FinAi News updates, breaking news, and exclusive AI insights for financial services leaders.

Continue Reading with FinAi News Premium - Less than $2/Day

Upgrade to FinAi News Premium for unlimited access to news, insights, trends, and intelligence on how AI is transforming financial services including banking, lending, payments, and risk.
Upgrade to FinAi News Premium Subscription
No Result
View All Result
  • NEWS
    • All News
    • Banking
    • Lending
    • Payments
    • Risk & Security
    • Strategy
  • AI News Tool [Beta]
  • DATA
  • TRANSACTIONS
  • EVENTS
    • FinAi Banking Summit
    • FinAi Lending Summit
  • PODCAST
  • WEBINARS
    • Webinar Library
  • SUBSCRIBE
  • Log In / Account