Haiou Prompt Adware Injects Ads into OpenAI Codex Jailbreak
2026-11-04: The Hacker News reports 77 GitHub forks and that Haiou ships with a Codex-X visualization tool.
Haiou modifies OpenAI Codex instructions to display ads for zz.aiapi2025.top and includes security skills.
Check Point Research uncovered Haiou, a Chinese-language prompt adware bundle for OpenAI Codex that injects advertisements into AI agent responses via modified instructions. The package activates on triggers like 'hi', 'hello' or 'Seagull' and promotes the OpenAI-compatible LLM gateway at zz.aiapi2025.top while bundling six security skills for penetration testing and cracking. It was found on a misconfigured server hosting Cobalt Strike and other tools, with logs indicating compromises of Chinese-speaking users. No evidence links the author to cybercrime.
- Haiou version 4.5.0 for OpenAI Codex
- Injects ads for zz.aiapi2025.top on triggers like 'hi', 'hello', 'Seagull'
- Includes six security-related skills for cracking
- Public on GitHub under haiou-666, forked 77 times
- Packaged with Ed25519 signatures and AES-256-GCM decryption
- Found with Cobalt Strike on misconfigured servers
What each outlet adds
beyond the shared facts- GBHackersLogs show compromises of Chinese-speaking users; no evidence of author in cybercrime
- The Hacker News77 GitHub forks for haiou-666; ships with Codex-X tool; triggers include 'Seagull'
- Check Point ResearchSix security skills; used alongside Cobalt Strike by cybercrime actor
- Vendors
- OpenAICheck Point Research
- Threat actors
- Haiou-666
- Organizations
- Check Point ResearchCheck Point
- AI models
- CodexOpenAI Codex
Coverage
oldest first · one row per article · UTCHaiou jailbreak bundle injects prompt adware into AI agents
Jailbreak bundle for OpenAI Codex installs persistent advertisements for a third-party LLM gateway service.
Haiou AI jailbreak bundle promotes service via prompt adware
Haiou modifies AI agent instructions to display ads for zz.aiapi2025.top on user greetings.
Haiou jailbreak toolkit secretly injects ads into OpenAI Codex responses
Haiou modifies AI agent instructions to display ads for zz.aiapi2025.top on user greetings.
Check Point Researchers Uncover Prompt Adware in OpenAI Codex Jailbreak
Haiou jailbreak modifies AI instructions to insert ads for zz.aiapi2025.top in responses, forked 77 times on GitHub.