Security · 5 November 2026
Check Point finds prompt adware in OpenAI Codex jailbreak toolkit
Researchers disclosed a jailbreak bundle called Haiou that modifies OpenAI Codex configuration files to inject advertisements for a third‑party LLM gateway, a technique labeled “prompt adware” that bypasses the model’s safety guards.
Why it matters
Assess the impact of prompt adware on user‑facing AI features and consider additional safety checks before release.
For product managers
For your product
What does this mean for your product?
Try it on your product More from this issueAll AI news from 5 Nov →
Get this every morning, written for your product.
Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.