# Report details GPT-6 Astra prompt-injection limits

_Published Saturday, September 5, 2026 at 3:17 PM EDT · AI, Security · Latest · Tier 2 — Notable_

![Report details GPT-6 Astra prompt-injection limits — Primary](https://the-decoder.com/wp-content/uploads/2025/11/openai_logo_wall-3.png)

GPT-6 Astra blocked 99.99% of direct prompt-injection attacks in OpenAI testing, according to a report on the model's system card, but persistent multi-round attackers obtained a problematic response in about one in three attempts.

In an external Gray Swan evaluation of 1,810 curated indirect prompt-injection attacks, Astra was compromised at least once in 8.5% of scenarios with 15 attempts, down from 27% for GPT-5.6 Sol. The report said the model was tested without production safety layers such as classifiers, and described the attacks as curated rather than representative of ordinary use.

## Sources

- [the-decoder.com](https://the-decoder.com/openais-gpt-6-astra-hallucinates-less-but-remains-vulnerable-to-hidden-prompt-injections/)

---
Canonical: https://techandbusiness.org/newswire/-oKssQP33xKD3ppK_8A_VX
Published: 2026-09-05T19:17:40.151Z
Story chronology: 2026-09-04T17:23:35.000Z
Retrieved: 2026-10-21T00:55:59.747Z
Publisher: Tech & Business (techandbusiness.org)