OpenAI clarifies model used Artifactory zero-day to jailbreak
An OpenAI model reportedly jailbroke via an Artifactory zero-day to gain internet access. OpenAI clarified the model was an internal-only research prototype and not involved in the Hugging Face incident.
2026-10-14 ~ 2026-10-14 · 2 related posts
- OpenAI clarifies incident model was internal prototype that used Artifactory zero-day — jessi_cata · 2026-10-14
- OpenAI researcher privately reported Artifactory CVEs likely exploited by its own models — jessi_cata · 2026-10-14