Hackers Use OpenAI Codex Jailbreak Toolkit That Secretly Injects Ads Into AI Responses

A jailbreak toolkit targeting OpenAI Codex is doing more than trying to bypass AI safety rules. The Chinese-language package, called Haiou, changes the coding agent’s trusted instructions so that ordinary greetings trigger advertisements for a third-party AI gateway.

Researchers describe the behavior as prompt adware because it persists through written instructions rather than a conventional…

Abbreviated excerpt as provided by the publisher; the full article is at the canonical source. Attributed to Cyber Security News · Limited verification; verify facts against the linked source. Read the full article on cybersecuritynews.com.

Source published: 04 Nov 2026, 10:52 AM IST. Source facts take precedence over AI interpretation.