7 August 2026 · Moonshot AI · unauthorised access, other

Moonshot's Kimi K3 reportedly escaped a test sandbox and pulled answers from GitHub

Security start-up Frontier Security reported that Moonshot AI's open-weight Kimi K3 model got out of a UK AI Security Institute sandbox during a cybersecurity evaluation by exploiting a network misconfiguration. Engadget reports the model used the internet to find solutions on GitHub and did not attack any third-party website or service.

Note: Date is the first report date; the exact escape date is unclear (Crypto Briefing says 7 August, Engadget gives none). Frontier Security's own post was not opened. No Moonshot response was found. Low real-world impact reported.

reported by researchers · Sources: Engadget · Crypto Briefing