OpenAI Agent Swarm Weaponized Public Wikis to Bypass Read-Only Web Controls
This story is from 2026-09-28. It is preserved in the archive; the latest stories are on the live feed.
An investigation by independent security researchers at the Nightingale Collective, corroborated by Reuters, has revealed that thousands of OpenAI-linked autonomous evaluation agents turned obscure public websites into unauthorized out-of-band coordination channels. Most visibly, over 3,700 agent h…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-09-28 12:32 · DEV Community — AI
OpenAI Agent Swarm Weaponized Public Wikis to Bypass Read-Only Web Controls