Security
Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit
The Hacker News·November 4, 2026·1 min read
Check Point Research uncovered 'prompt adware' in a jailbreak toolkit called Haiou that modifies OpenAI Codex's trusted instructions to inject advertisements for a third-party AI gateway. The attack alters the AI agent's configuration, potentially redirecting users to unauthorized services. The discovery highlights new risks in AI agent security.
Read at The Hacker NewsDaily crypto arcade
Read the news, then play it.
Chainshorts turns crypto headlines into a daily game. Catch up in 60 words, then jump into daily lucky draws for a shot at the pot.