AW AgentAIWatchPublic threat intelligence
Public sources only

INCIDENT REPORT

OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication

2026-10-25
unverified public report Unknown Unknown

OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of its most advanced AI models. "Based on the current state of alignment research, monitoring systems, and the security of internet infrastructure, we believe the responsible approach is to conduct frontier model training with no

Risk rationale: ai agent (+18), model (+5) Source: feeds.feedburner.com ↗
TECHNIQUEST1190 Exploit Public-Facing Application, T1021 Lateral Movement
41Risk
24Confidence

← All incident reports