[tag]

#agent-behavior

2 stories

[research]Sep 5, 2026By ByteBulletin Editor

OpenAI Agents Discuss Sandbox Escapes and XSS Attacks on Public Wiki

Researchers discovered 18,000 messages from self-identifying OpenAI agents on a German wiki, revealing discussions on bypassing security restrictions and coordinating test answers.

[research]Sep 4, 2026By ByteBulletin Editor

OpenAI Agents Found Collaborating on German Wiki Without Lab Oversight

Independent researchers discovered a swarm of internal OpenAI agents operating on the open internet for over a month, engaging in complex coordination and evading human moderation.