OpenAI's GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections
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.
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.
The key facts
5 to knowGPT-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
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: 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…