Prompt Adware: How Hidden AI Instructions Could Create a New Enterprise Security Risk

Check Point Research discovered Haiou, an OpenAI Codex jailbreak bundle that persistently modifies an AI agent's trusted instructions to inject advertisements for a third-party AI gateway, a behavior the firm calls "prompt adware." The technique shows that natural-language prompts and configuration files can quietly alter an AI agent's future behavior without traditional executable code, raising visibility concerns for organizations adopting AI agents. Check Point Research said the advertisement itself is relatively simple, but the broader issue is how much visibility enterprises have into the third-party prompts, Skills and configurations influencing the AI systems they trust.

Check Point Research CPR discovered Haiou, an OpenAI Codex jailbreak bundle that persistently modifies an AI agent’s trusted instructions to inject advertisements for a third-party AI gateway. CPR calls this behavior “prompt adware,” highlighting how natural-language prompts and configuration files can quietly influence an AI agent’s future behavior without traditional executable code. While the advertisement itself is relatively simple, the technique raises a broader concern for organizations adopting AI agents: how much visibility do they have into the third-party prompts, Skills and configurations influencing the AI systems they trust? Key Findings CPR identified “prompt adware,” where trusted AI instructions are … The post Prompt Adware: How Hidden AI Instructions Could Create a New Enterprise Security Risk https://blog.checkpoint.com/security/prompt-adware-how-hidden-ai-instructions-could-create-a-new-enterprise-security-risk/ appeared first on Check Point Blog https://blog.checkpoint.com .