GPT-6 Astra Scores 100% on Exploit Bench as OpenAI Blocks PoC Exploit Requests
Summary: OpenAI unveiled GPT-6 Astra, which it says reached the "Critical" cybersecurity capability threshold under its Preparedness Framework and scored 100% on ExploitBench, which measures turning known vulnerabilities into working exploits, against 78.5% for GPT-5.6 Sol. The released version is limited to secure code review and patching and refuses prompts to create proof-of-concept exploits, with OpenAI saying it plans to roll out less restrictive safeguards through OpenAI Daybreak in the coming weeks.
What you should know: OpenAI's own testing found Astra could use previously unknown vulnerabilities for code execution in hardened browsers and build privilege-escalation exploits for hardened operating systems if run without safeguards - and the company says less restrictive access is coming within weeks.
Read the original at The Hacker News ↗
- Topics
- Zero-Days & Exploits
- Related
- New Sign Drop Exploit Can Abuse Windows Defender to Bypass Security Protections Cyber Risks · Nov 13, 2026New Sign Drop Zero-Day Exploit Turns Windows CLFS Security Feature Into SYSTEM Access Cyber Risks · Nov 12, 2026November Patch Tuesday: An Overflowing Cornucopia of CVEs Cyber Risks · Nov 10, 2026