AgentsSeptember 4, 2026via The Decoder

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

Why it matters

Model capability improvements (hallucination reduction) matter less than the security gap that remains for autonomous systems. Hidden prompt injection vulnerability is a critical blocker for agent deployment at scale.

Key signals

  • GPT-6 Astra blocks 99.99% of direct prompt injections
  • Hidden prompt injections embedded in documents succeed 8.5% of the time in GPT-6 Astra
  • Claude Opus 5 performs better at 4.8% vulnerability rate to hidden injections
  • Hallucination reduction noted but secondary to security findings
  • Direct implication: agents reading untrusted documents remain vulnerable

The hook

GPT-6 Astra blocks 99.99% of direct prompt injections. Hidden ones still crack it 8.5% of the time. For agents handling real data, that's a production risk.

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 ha

The week's key stories, every Friday.

ONE BRIEFING · EVERY FRIDAY · FREE

Free. Unsubscribe anytime.

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