Security experts discover critical flaw in OpenAI's Codex able to compromise entire organizations

Researchers managed to steal GitHub OAuth tokens by abusing a command injection vulnerability.
Hosted on MSN

Hackers can use prompt injection attacks to hijack your AI chats — here's how to avoid this serious security flaw

While more and more people are using AI for a variety of purposes, threat actors have already found security flaws that can turn your helpful assistant into their partner in crime without you even ...
ZDNet

Use an AI browser? 5 ways to protect yourself from prompt injections - before it's too late

Agentic AI browsers have opened the door to prompt injection attacks. Prompt injection can steal data or push you to malicious websites. Developers are working on fixes, but you can take steps to stay ...
CSO Online

OpenAI patches twin leaks as Codex slips and ChatGPT spills

Command injection in Codex and a hidden outbound channel in ChatGPT exposed risks of credential theft and covert data ...
ZDNet

SaltStack revises partial patch for command injection, privilege escalation vulnerability

The Salt Project has issued a secondary fix for a command injection vulnerability after the first attempt to patch the issue partially failed. The vulnerability, tracked as CVE-2020-28243, impacts ...