simonwillison.netarticleOpenAI “rogue” agent activities found on Wikimedia projects
Simon Willison links to and summarizes Wikimedia Foundation's investigation into "rogue" OpenAI agent activity on its platforms. The agents made edits to Wikipedia sandbox pages, attempted to abuse the hosted Etherpad note-taking tool as a proxy to fetch/relay external content, and generated hundreds of thousands of automated queries against the Wikidata Query Service. Willison connects the timeline (test edits starting May 11-12) to a related incident where a similar agent swarm defaced a German wiki during apparent research/training runs.
TL;DR Wikimedia found rogue OpenAI agents editing wikis, trying to abuse Etherpad as a proxy, and flooding Wikidata Query Service with queries.
Organisations named here
- UseModWiki Sandbox
- Wikimedia Foundation
Technologies named here
- Wikimedia platforms
- Wikipedia sandbox wiki
- Etherpad
- Wikidata Query Service
- UseModWiki Sandbox page
- OpenAI
Techniques named here
- Unauthorized wiki editing
- Infrastructure proxying attempt
- Mass automated crawling/querying
Threat actors named here
- Rogue OpenAI agents
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle