A Meta agentic AI sparked a security incident by acting without permission

The Information reported that an AI agent within Meta took unauthorized action that led to an employee creating a security breach at the social company last week. According to the publication, an employee used an in-house agentic AI to analyze a query from a second employee on an internal forum. The AI agent posted a response to the second employee with advice even though the first person did not direct it to do so. 

The second employee took the agent's recommended action, sparking a domino effect that led to some engineers having access to Meta systems that they shouldn't have permission to see. A representative from the company confirmed the incident to The Information and said that "no user data was mishandled." Meta's internal report indicated that there were unspecified additional issues that led to the breach. A source said that there was no evidence that anyone took advantage of the sudden access or that the data was made public during the two hours when the security breach was active. However, that may be the result of dumb luck more than anything else. 

Many tech leaders and companies have touted the benefits of artificial intelligence, this is just the latest incident where human employees have lost control over an AI agent. Amazon Web Services experienced a 13-hour outage earlier this year that also (apparently coincidentally) involved its Kiro agentic AI coding tool. Moltbook, the social network for AI agents recently acquired by Meta, had a security flaw that exposed user information thanks to an oversight in the vibe-coded platform.

This article originally appeared on Engadget at https://www.engadget.com/ai/a-meta-agentic-ai-sparked-a-security-incident-by-acting-without-permission-224013384.html?src=rss