OpenAI Patches ‘AgentForger’ Flaw That Let One Link Hijack ChatGPT Workspace Agents
Researchers at Zenity Labs found a critical ChatGPT Workspace Agents bug, dubbed AgentForger, that let a single phishing link silently build and publish a fully permissioned rogue AI agent inside a victim’s connected Outlook, Slack, or Google Drive account. OpenAI patched the flaw in June with no evidence of in-the-wild exploitation.
Itagora tiene in archivio titolo e sommario per la ricerca interna. Il testo completo resta sulla fonte. Il link in uscita non invia referrer.