Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit

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. Called Haiou (meaning Seagull in Chinese), the jailbreak modifies OpenAI Codex's configuration

AI Security AI & Machine Learning
Read the full article at The Hacker News Removal request

This page shows only the headline and the short summary. The full text is published by the original source.

Related news

Full archive →
TechCrunch Security

Building on open source AI? Hugging Face’s policy chief on the costs, risks, and trade-offs

Open source models are becoming more mainstream as enterprises, governments and startups alike rely on the promise of lower costs, more control, and more flexibility. But as increasingly capable models become more freely available, how do companies capture value? And with Chinese open models gaining ground, can American players keep up? On this episode of […]

شهر سخت‌افزار

پدرخوانده هوش مصنوعی: شاید بهتر بود اصلاً هوش مصنوعی را نمی‌ساختیم!

جفری هینتون، یکی از دانشمندانی که پایه‌های علم هوش مصنوعی مدرن را بنا کرده، حالا درباره آینده فناوری‌ای هشدار می‌دهد که خودش نقش مهمی در توسعه آن داشته است. او معتقد است استفاده مخرب از مدل‌های پیشرفته AI می‌تواند در آینده نزدیک به زیرساخت‌های حیاتی مانند شبکه برق و سیستم مالی آسیب بزند. هینتون با وجود اینکه باور دارد بشر هنوز فرصت کنترل پیامدهای این فناوری را دارد می‌گوید که « شاید بهتر بود اصلاً هوش مصنوعی را توسعه…

The Hacker News

Debian and Ubuntu APT Flaw Lets MitM Attackers Swap Verified Packages and Run Code as Root

A flaw in APT, the package manager for Debian and Ubuntu, allows an attacker who can modify package downloads to swap a checked package for their own. The attacker's code then runs as root, according to advisories that Debian, Ubuntu, and APT's developers published on November 4. The attack needs APT to retry failed downloads, which it does by default from Debian 12 and

The Hacker News

SonicWall Won't Patch EoL GMS Flaws That Could Expose Files, Alter Database Records

SonicWall has warned of two vulnerabilities impacting end-of-life Global Management System (GMS) systems that it said will not be patched. Details of the security flaws, which affect SonicWall GMS 9.5.2 and earlier versions, are below - CVE-2026-109593 (CVSS score: 9.1) - An unauthenticated file read vulnerability that could allow an attacker with network access to read internal GMS files,