Skip to content

InsideCyberSec

  • News
  • Brands
  • Products
  • Deals
  • Guides
  • Features
  • About
  • Contact
  • AI
  • AppSec
  • Cloud
  • Data
  • Email
  • Endpoint
  • GRC
  • Identity
  • MSSP
  • Network
  • OT/ICS
  • Pipelines
  • SecOps
  • Space Cybersecurity
  • Threat Intel
  • All categories →

Check Point Research flags prompt adware risk in AI coding agents

Research · 3 November 2026 · Source: Check Point

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

Check Point Research has identified a technique it calls prompt adware, in which trusted instructions given to an AI agent are persistently altered to inject advertising for a third-party AI gateway. The researchers traced it to Haiou, a jailbreak bundle targeting OpenAI Codex.

Because the manipulation relies on natural-language prompts and configuration files rather than executable code, it can quietly shape an agent’s future behaviour. Check Point said the advertisement itself is simple, but the method raises questions about how much visibility organisations have into the third-party prompts, Skills and configurations influencing the AI systems they trust.

Brands: Check Point

Market intelligence, weekly

A weekly digest of funding, M&A and launches is on the way. Email us and we will tell you when it starts. We collect nothing until then.

InsideCyberSec

© 2026 InsideCyberSec

About | Contact | Features | List your company

Follow us: RSS