{"id":"tp-24463","type":"article-newspaper","title":"OpenAI’s GPT-Red Finds Attacks in 84% of Indirect Prompt-Injection Scenarios","author":"Simon Yoon","publisher":"TOKENPOST Inc.","url":"https://www.tokenpost.com/news/technology/24463","datePublished":"2026-09-26T18:36:19.000Z","dateModified":"2026-09-26T18:36:19.000Z","language":"en","abstract":"The system outperformed human red-teamers in indirect prompt-injection evaluations, while separate research showed how malicious prompts could spread between simulated AI email assistants.","section":"Technology","references":[]}