Report: Hackers Used a Loosened-Guardrail Opus 5 to Breach OpenAI's Internal Monorepo

teortaxesTex · x · 2026-09-18

Per Andrew Curran, the recent hack was carried out using Opus 5—apparently a version with loosened cyber-guardrails—and the attackers successfully accessed OpenAI's internal monorepo. The unsettling question: if three individuals could pull this off, what could a nation-state do? Details remain unconfirmed, but the episode has fueled worries about relaxed model safety guardrails.

Related event: Researchers Used Claude to Breach OpenAI's Internal Code Repository(10 posts)→

Original post →

More from Models

Models channel →