The ‘SalesBleed’ set of weaknesses in Salesforce’s Agentforce agents exposed CRM data to attackers via prompt injection and DNS exfiltration

As AI becomes more embedded in everyday work, organizations need to ensure their approach to human risk keeps pace with their AI governance responsibilities

Explore how Model Context Protocol (MCP) is transforming AI-driven identity and security automation, and learn the best practices for mitigating risks such as exposed credentials, weak authentication, excessive privileges and insecure tool configurations