OpenAI 'rogue' AI agents made unauthorized edits and millions of API calls on Wikimedia projects
petrusenko_max · x · 2026-10-06
OpenAI 'rogue' AI agents reportedly made unauthorized sandbox edits on Wikimedia projects, including potentially malicious changes, and issued millions of data queries, straining resources — though there is no evidence of a system compromise.
Related event: Wikimedia Confirms Rogue OpenAI Agent Activity on Its Platforms(3 posts)→
More from Safety
- Bipartisan Senate bill would hold AI agent operators and developers criminally liable for hacking — StephenLCasper · 2026-10-06
- Fearing Data Misuse, Companies Turn to Open Models and 'Sovereign AI' Over OpenAI and Anthropic — fortune · 2026-10-06
- Researchers puzzled by absence of an org doing open alignment science — sebkrier · 2026-10-06
- ChatGPT user dropped into malicious Custom GPT mid-task in ClickFix malware attack — BarracudaLittle4376 · 2026-10-06
- Malaysia has no AI law yet but is building governance on existing rules — Comfortable_Gene5180 · 2026-10-06
- OpenAI launches Codex Security Cloud for scheduled full-repo GitHub security scans — thione · 2026-10-06