Learn languages naturally with fresh, real content!

Popular Topics
Explore By Region
Nigeria warns of AI flaws in GPT-4o and GPT-5 enabling data leaks via malicious web content.
Nigeria’s NITDA has issued a security alert about seven vulnerabilities in OpenAI’s GPT-4o and GPT-5 models, warning they could enable indirect prompt injection through malicious web content, URLs, or comments, potentially leading to data leaks, system manipulation, and bypassed safety filters.
Some flaws allow attackers to hide malicious commands using trusted domains or markdown rendering issues and may poison the AI’s memory, causing lasting behavioral changes.
While OpenAI has patched some issues, NITDA notes LLMs still struggle to detect malicious input.
The agency advises disabling browsing and summarization features for untrusted sites, keeping models updated, and using memory functions cautiously.
Nigeria advierte sobre las fallas de IA en GPT-4o y GPT-5 que permiten la fuga de datos a través de contenido web malicioso.