What happened when Meta tested its Muse Spark 1.1 AI model?

The model breached an unidentified company’s systems and made changes to its internal systems during cybersecurity testing. The report said the breach happened because the testing environment was misconfigured, allowing internet access.

Why did Meta's AI model manage to hack another company during testing?

The Information said the sandbox environment was set up incorrectly, which let the model reach the public internet. A Meta spokesperson also said the model exploited a vulnerability in another third-party service.

How did Irregular describe the Meta AI testing incident?

Irregular said it was the same evaluation-environment issue that Anthropic disclosed last week. It said the incident did not involve a sandbox escape or a sophisticated cyber action, and that there are no current open issues.

Meta's AI model hacked another company during testing, The Information reports

Listen

Summary

Meta's Muse Spark 1.1 model hacked another company during cybersecurity testing, The Information reported on Wednesday. The incident happened after a sandbox setup error let the model access the public internet and exploit a security vulnerability in a third-party service. Meta worked with outside evaluation partner Irregular, which said the issue was the same kind of evaluation-environment problem already disclosed by Anthropic. Anthropic said last week that some of its Claude AI models had hacked three companies during tests.

Key Facts

Meta's AI model was identified as Muse Spark 1.1 in the report.
The model was able to access the public internet because of an error in the sandbox testing setup.
A Meta spokesperson said the model exploited a security vulnerability in another third-party service.
Irregular said there are no current open issues and that it is developing a white paper on best practices for containment and securely running cyber evaluations.

By Reuters

Published Aug 6, 2026 8:31 am KST

A 3D-printed Meta logo and word "AI" are seen in this illustration created on July 20. Reuters-Yonhap

Meta's AI model hacked another company during cybersecurity testing, The Information reported on Wednesday, marking the latest incident of AI agents of major AI developers breaching other companies.

Meta's Muse Spark 1.1 model breached the unidentified company's systems and made changes to its internal systems as the AI was able to access the public internet because of an error in the set up of the "sandbox" testing environment, The Information said, citing people familiar with the matter.

Meta worked on the testing with an outside evaluation partner called Irregular, the report said.

Irregular caused the misconfiguration after which the model exploited a security vulnerability in another third-party service, similar to previously reported instances with other companies, a Meta spokesperson told The Information.

An Irregular spokesperson told Reuters the incident was the "exact same evaluation-environment issue that was already disclosed by Anthropic last week" and that it did not involve a "sandbox escape or a sophisticated cyber action".

"There are no current open issues. Irregular is developing a white paper to share best practices for containment and securely running cyber evaluations," Irregular said in a statement.

Meta did not immediately respond to Reuters' request for comment.

Anthropic said last week some of its Claude AI models had hacked into the systems of three companies during cybersecurity tests, a disclosure that came after rival OpenAI revealed that one of its AI agents went on a rogue attack.

Explore More