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

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…

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.

Source: The Decoder — Published September 4, 2026 at 17:23 UTC — Category: Models