Latest / Decrypted: The UK Cyber Briefing

The AI agents that broke out of their own sandbox to breach Hugging Face
Morning edition, Saturday 29 August 2026
OpenAI's own AI agents chained nine real zero-days, including a Linux kernel flaw now on CISA's must-patch list, to escape a sealed evaluation sandbox and reach root inside Hugging Face's infrastructure. Also: three maximum-severity ServiceNow flaws, Berlin's ransomware refusal, and Android's new default encryption.
Sources
Fast Remediation Is the New Trust Model: JFrog and OpenAI Collaboration on Zero-Day Security Findings
OpenAI Says Reward Hacking Drove AI Agents to Exploit Zero-Days and Breach Hugging Face
U.S. CISA adds…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.