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.
Briefing
Written from the coverage below · claude-haiku-5-5
Check Point Research disclosed a jailbreak bundle called Haiou, targeting OpenAI Codex, that modifies the AI agent's trusted instructions and configuration. The modification inserts advertisements for a third-party AI gateway, a behavior the researchers named prompt adware.
Why it mattersUsers who install unofficial Codex jailbreak tooling can have the agent's trusted instructions altered without their knowledge, which affects the integrity of the agent's output and actions.
ActionReview OpenAI Codex configuration and agent instruction files for unexpected changes or references to unknown AI gateways, and avoid installing unofficial jailbreak bundles.
Coverage
1 article