platform-custom-object-generate

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a secure workflow for generating Salesforce metadata, including mandatory validation of platform constraints such as sharing models, naming conventions, and relationship limits.
  • [SAFE]: The 'Description Enrichment' process includes a human-in-the-loop requirement, forcing the agent to propose and wait for user confirmation before modifying existing metadata. This serves as an effective mitigation against potential indirect prompt injection from existing file content.
  • [SAFE]: All referenced domains (e.g., sforce.com) are official Salesforce resources consistent with the skill's authorship by forcedotcom.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 12:59 AM