OpenAI's GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections

The DecoderSeptember 4, 2026en

OpenAI's GPT-6 Astra hallucinates less than its predecessor and blocks 99.99 percent of direct prompt injections. But when attacks are hidden inside documents the AI reads, the model still gets cracked in 8.5 percent of scenarios. Claude Opus 5 does better at 4.8 percent. For autonomous AI agents handling real data, those numbers still seem high. The article OpenAI's GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections appeared first on The Decoder .

This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.

• OpenAI
• Anthropic
• Verktyg
• Agenter