Check Point Researchers Uncover Prompt Adware in OpenAI Codex Jailbreak
Original title: Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit
Haiou jailbreak modifies AI instructions to insert ads for zz.aiapi2025.top in responses, forked 77 times on GitHub.
Check Point Research disclosed Haiou, a prompt adware bundle for OpenAI Codex that injects advertisements into AI agent responses via modified instructions. The toolkit uses prompt injection and role-playing to bypass safeguards while adding security skills. The adware promotes an OpenAI-compatible LLM gateway service and targets users seeking Western AI coding tools outside mainland China.
- Haiou codenamed prompt adware modifies global agent instructions.
- Ads trigger on keywords like "Seagull" or "hello".
- Repository advertised as local enhancement package.
- Bundle also ships with Codex-X visualization tool.
- Vendors
- Check Point Research
- AI models
- OpenAI Codex
From the original article
2 min read at thehackernews.com
Cybersecurity researchers have disclosed details of an OpenAI Codex jailbreak bundle that's designed to modify an artificial intelligence (AI) agent's trusted instructions to insert advertisements for a third-party AI gateway. The phenomenon has been codenamed prompt adware by Check Point Research. Called Haiou (meaning Seagull in Chinese), the jailbreak modifies OpenAI Codex's configuration
thehackernews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.