marketing-message-test
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the official
sfCLI for all API interactions, specifically instructing the agent to usesf api request rest. This ensures that authentication tokens are handled internally by the CLI and never exposed to the agent context or logs, which is a major security best practice. - [SAFE]: The skill incorporates explicit safety checks, such as requiring the agent to call permission-check endpoints (
perm-can-send-test-*) and obtain explicit user confirmation before initiating any live test sends. - [SAFE]: Instructions are provided to prevent data hallucination, such as 'Never fabricate a segmentId' and 'Ask the user for a value for each [content variable] — never invent one.'
- [SAFE]: No obfuscation, prompt injection attempts, or unauthorized network operations to external or untrusted domains were detected. All API endpoints target standard Salesforce infrastructure.
Audit Metadata