SPIN Unprocessed
Source The Decoder the-decoder.com Media Center
September 4, 2026 ai_technology ai

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

View original on the-decoder.com

Overview

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.

SpinGraph analysis pending — check back after processing.

Ask AI about this story

Opens with the SpinGraph .md URL and structured context — one click, prompt included.

More from The Decoder

View all →

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO