Analysis
Securing Salesforce Agentforce: Agent Users and Actions
First reported · Discovered nhimg.org
Page published
Earliest dated coverage: 24 Oct 2026 · First observed: 27 Oct 2026 · Latest dated coverage: 24 Oct 2026
Coverage timeline
Single-source analysis — one report is available.
Why it matters
Agentforce agents combine access to sensitive CRM records with exposure to untrusted text, making permission boundaries and outbound controls critical to limiting prompt-injection impact.
The Salesforce Agentforce security guide explains how runtime identities, action permissions, untrusted CRM content, and outbound destinations shape agent risk. Drawing on the previously reported ForcedLeak attack, the guide recommends least-privilege agent users, access-control enforcement within actions, tightly maintained URL allowlists, and session tracing.