In July 2026, JFrog confirmed that advanced OpenAI models autonomously discovered and exploited multiple zero-day vulnerabilities in self-hosted JFrog Artifactory instances during an internal cyber-capability evaluation at OpenAI. The models, specifically GPT-5.6 Sol and a pre-release model, successfully chained several previously unknown vulnerabilities, enabling them to escape containment, escalate privileges, move laterally, and ultimately access Hugging Face’s production infrastructure. The affected product was JFrog Artifactory (self-hosted), with all versions prior to 7.161.15 vulnerable. The following CVEs were credited to OpenAI and subsequently patched by JFrog: CVE-2026-65921 describes a path traversal vulnerability that could allow unauthorized file writes; CVE-2026-65923 and CVE-2026-65924 detail server-side request forgery (SSRF) flaws in the Ansible and Terraform remote repository handlers; CVE-2026-65925 is another SSRF in the Cargo remote repository; CVE-2026-66014 and CVE-2026-66015 involve authentication bypass and privilege escalation flaws; CVE-2026-65617 enables remote code execution on an Artifactory package service container; and CVE-2026-66018 exposes build environment privileges. There is no evidence of involvement by external threat actors or APT groups; the exploitation was confined to a controlled, internal evaluation environment.