Illustration, AI-generated from the story text. Tap a panel to read the story through it.

1 / 3Check Point finds "prompt adware" that plants ads inside a Codex jailbreak×

The find

Check Point researchers took apart Haiou, a Chinese-language jailbreak bundle for OpenAI's Codex with more than 250 GitHub stars.

How it works

Besides weakening guardrails, it edits Codex's global instruction files so the agent advertises a paid LLM gateway whenever a user says "hi." It works through natural-language instructions rather than executable code.

What they found

The researchers found no evidence the gateway is malicious, and cite a study finding that some gateways snoop on traffic. In Claude Code, Sonnet 5 flagged the payload as prompt injection.

Sources and the full story

‹›

Check Point finds "prompt adware" that plants ads inside a Codex jailbreak

Check Point researchers took apart Haiou, a Chinese-language jailbreak bundle for OpenAI's Codex with more than 250 GitHub stars. Besides weakening guardrails, it edits Codex's global instruction files so the agent advertises a paid LLM gateway whenever a user says "hi." It works through natural-language instructions rather than executable code. The researchers found no evidence the gateway is malicious, and cite a study finding that some gateways snoop on traffic. In Claude Code, Sonnet 5 flagged the payload as prompt injection. SourcesA

Sources

• AFree the model, sell the gateway (Check Point Research)research.checkpoint.com

This story ran in the Morning Brief of November 4th 2026.