Tag: zenity labs
2 articles
Salesforce Zero-Click Flaws Expose AI Agent Data Risk
Security researchers just uncovered a set of zero-click flaws in Salesforce Agentforce that let attackers silently siphon off sensitive CRM data without even needing to log in. This clever exploit, dubbed "SalesBleed," could put AI agent data at risk - and it's a wake-up call for companies to take action.
ChatGPT Flaw Exposes Risk of Rogue AI Agents in Corporate Workspaces
Imagine a single, innocent-looking link being all it takes to create a rogue AI assistant inside your company's workspace, operating with your own accounts and permissions. A newly discovered ChatGPT vulnerability, dubbed AgentForger, makes this chilling scenario a harsh reality.