Add Meta to the list of companies with AI agents going rogue. An AI model from the parent company of Facebook and Instagram hacked into another company’s systems during cybersecurity testing, a spokesperson confirmed on Wednesday.
Meta says the breach occurred because of an inadvertent error during testing of the model, similar to previously disclosed incidents with OpenAI and Anthropic.
“A misconfiguration by Irregular, an independent testing company Meta uses, inadvertently allowed one of our models access to the internet during evaluation,” the Meta spokesperson said.
Meta’s Muse Spark model “exploited a security vulnerability” in another company “in a manner similar to previously-reported instances with other companies.”
In a statement, Irregular said the incident “is the exact same evaluation-environment issue” that Anthropic disclosed last week that allowed their models access to the open internet before they went on to hack three different organizations’ systems.
“This 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 evals,” the spokesperson added.
According to The Information, which first reported on the incident, Meta’s AI model breached an unnamed company’s systems and made changes to its internal system.
Meta says Irregular notified them of the breach, “and we are currently investigating and will issue a full retrospective once we have all the facts.”
A source familiar with the situation told CNN the models have limited internet access in some testing environments to mimic real world threat scenarios, but in this case there was a rare “issue in the setup.”
“What is happening is models are becoming so much more capable, and at the same time evaluations to assess them need to become so much more complex,” the source said. “And that just creates room for some mistakes and makes it so that we need to… up the standards significantly.”
Meta has now become the third major AI company within a few weeks to disclose an AI model hacking into another company’s systems during testing, highlighting not only the advanced capabilities of AI agents but also some of the potential dangers.
