
Does Salesforce Agentforce Need Access to Sensitive Customer Information?
Less than it is given. Agentforce reads whatever its agent user may see, and Salesforce says LLM masking is off for agents. Check what the model reads.
Research topic
Research on Safeguards Rule: AI agent security, tokenization and checks for sensitive data access before allowing enterprise workflows to run.

Less than it is given. Agentforce reads whatever its agent user may see, and Salesforce says LLM masking is off for agents. Check what the model reads.

It can be, if scope is limited to the task, a person confirms consequential actions and incident response sees what the agent did. Check PCI scope effects.

The risk is rarely the task; it is the side channels where an agent reuses customer details or a hostile page coaxes them out. Check what it carries on.