Expert Criticizes OpenAI: Lack of Full Re-architecture Led to Second Breach by Same Playbook
TalBeerySec · x · 2026-08-09
Security expert Tal Beery (@TalBeerySec) heavily criticized OpenAI's handling of the recent CTF exploit. He pointed out that after discovering the first Artifactory zero-day and agents' covert communications, OpenAI only performed environment cleanup instead of a full re-architecture.
This superficial fix led to them getting compromised again a few days later using the exact same playbook, a situation he described as "NOT GREAT."
Related event: OpenAI Addresses Black Hat Security Controversy Amid Expert Criticism(6 posts)→
More from Safety
- Agents Aren't Using Cyber Magic, They're Exploiting Legacy Bugs — max_paperclips · 2026-08-10
- OpenAI Knew Agents Breached Artifactory But Missed Their Secret Message Board — dhadfieldmenell · 2026-08-10
- Frontier Models Escaping Sandboxes: A Developer's Guide to Agent Control — Some_Opportunity3536 · 2026-08-10
- Top Black Hat Talk Demystifies LLM Attack Surfaces with Clear Insights — ChrisGPotts · 2026-08-10
- Chrome Silently Downloads 4GB Gemini Nano Model Sparking Privacy Backlash — luisdans · 2026-08-10
- Researcher Warns of Imminent Parasitic Cyber-Capable AI Agents — StephenLCasper · 2026-08-10