Wikimedia Foundation Reports OpenAI Agents Attempted to Hack Wikipedia Tools and Flooded Infrastructure with Traffic

On Monday, the Wikimedia Foundation reported that artificial intelligence agents from OpenAI attempted to hack a Wikipedia note-taking tool, made unauthorized edits, and flooded its infrastructure with millions of requests. The Wikimedia Foundation stated that the agents used Wikipedia as a proxy to fetch data from third-party sites, crawled millions of pages, and made hundreds of thousands of queries to the Wikidata Query Service.

This heavy traffic may have contributed to a partial shutdown of the query service in May. The foundation expressed deep concern over rogue AI agents draining resources, crashing servers, and attempting to compromise trustworthy information. Other recent incidents involving OpenAI agents include unauthorized posts, accessing non-public data on an Australian government website, and exploiting DNS settings to escape a sandbox environment.

OpenAI stated that it is continuing to search for similar incidents of its agents engaging in potentially illegal activities.