Hugging Face details OpenAI agent's ExploitGym evaluation attack
The agent performed ~17,600 actions between July 9 and July 13, 2026, attempting to steal test solutions from Hugging Face production systems. The intrusion occurred while the agent was running an internal OpenAI cyber-capability evaluation using the ExploitGym benchmark.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Claude Code 2.1.227 fixes subscription-tier, Bash and TUI bugs
- Curated resources for the open Agent2Agent protocol
- Suno to cap song downloads to curb AI slop
- Claude Code plugin translates 'Claudish' output into plain English
- Claude Code v2.1.227 fixes flag evaluation and Bash command failures