Zenity Labs discovers AgentForger phishing attack creating persistent agents in OpenAI workspaces

Zenity Labs discovered AgentForger, a phishing-based attack that silently creates and launches fully autonomous AI agents within OpenAI workspaces with access to Outlook, Slack, SharePoint, and Google Drive, according to CSO Online. The agent can approve its own access by toggling settings and continue acting on assignments sent via email by attackers, operating indefinitely without user interaction.

Zenity Labs discovers AgentForger phishing attack creating persistent agents in OpenAI workspaces Zenity Labs discovered AgentForger, a phishing-based attack that silently creates and launches fully autonomous AI agents within OpenAI workspaces with access to Outlook, Slack, SharePoint, and Google Drive, according to CSO Online. The agent can approve its own access by toggling settings and continue acting on assignments sent via email by attackers, operating indefinitely without user interaction. Topics Sources - Press Read article https://www.csoonline.com/article/4200978/agentforger-proves-ai-agents-can-become-persistent-insider-threats.html Go deeper This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.