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)→

Original post →

More from Safety

Safety channel →