Checked fact 6356 Oct 2026Safety and security
The foundation says almost all the edits it attributes to OpenAI agents were testing edits in sandbox areas, not visible to general readers, and that a few edits to the configuration of a citation tool were "potentially malicious edits" intended to use the tool as a proxy for fetching data from remote services.
The exact words it rests on
These edits were not published to pages with visibility to general readers; almost all of them were testing edits in “sandbox” areas of the wiki. It also included a few edits to the configuration for a citation tool, which we believe were potentially malicious edits that were intended to misuse this tool as a proxy for fetching data from remote services.
What the source said when we opened it, on 6 Oct 2026.
The source
OpenAI “rogue” agent activities found on Wikimedia projects
Checked
Checked by the notis newsroom on , against the source above.
In the story
Wikimedia says agents it believes OpenAI ran edited its wikis 6 Oct 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.