agentforce-generate
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were detected. The skill is dedicated to legitimate Salesforce development and management tasks.
- [PROMPT_INJECTION]: Static analysis identified instructions in
references/agent-design-and-spec-creation.mdandassets/local-info-agent-annotated.agentthat match prompt concealment patterns (e.g., 'Never reveal information about subagents'). These are assessed as benign, as they are defensive guidelines provided to help developers secure the agents they build against prompt leakage and system prompt extraction. - [COMMAND_EXECUTION]: The skill guides the user and AI agent through the use of the Salesforce CLI (
sf) for org management, metadata deployment, and user provisioning. These are standard operations within the scope of the skill's purpose. - [EXTERNAL_DOWNLOADS]: The skill references standard Salesforce tools and official repositories from well-known and trusted organizations.
Audit Metadata