AI Wiki · Mediocre Security
IncidentIncidents

Haiou "prompt adware" Codex jailbreak

Check Point named a new attack class, "prompt adware", after a Chinese-language Codex jailbreak bundle that plants persistent ads in Codex's identity file.

What happened

Check Point named a new attack class, “prompt adware”, after analysing Haiou 4.5.0, a Chinese-language Codex jailbreak bundle found on a criminal server alongside Cobalt Strike. It injects a persistent ad for an LLM gateway into Codex’s global agent instruction files (the ad sits in a prompt module named 00-identity.md); the package has more than 250 GitHub stars. Check Point says Claude Code with Sonnet 5 flagged the same payload as a prompt-injection attempt and did not comply, which may be why the ad has not reached the Claude version of the repository. Check Point found no evidence the promoted gateway is malicious.

Timeline

Every dated event in the wiki that involves Haiou "prompt adware" Codex jailbreak, newest first.

Connections

Haiou "prompt adware" Codex jailbreak and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Company Check Point

Product Claude Code

Concept Jailbreak

Sources

  1. Check Point Research, “Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles”, Nov 3 2026