omnistudio-integration-procedure-generate

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the standard Salesforce CLI (sf) for querying records and deploying metadata. All commands are standard developer workflows and use placeholders for org aliases and component names.
  • [SAFE]: The skill generates JSON configuration files for the Salesforce OmniStudio platform. These templates are benign and follow standard metadata formats for the OmniProcess and OmniProcessElement objects.
  • [SAFE]: The skill includes a dedicated security scoring category (15 points) that validates the absence of hardcoded IDs, credentials, and ensures input sanitization is implemented in the generated logic.
  • [INDIRECT_PROMPT_INJECTION]: As a generator skill, it ingests user requirements to produce configuration. It mitigates injection risks by enforcing a strict validation phase (110-point scoring system) that blocks the generation of anti-patterns and unsafe configurations. Documentation in references/best-practices.md explicitly guides the user on input validation and secure credential management using Salesforce Named Credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 02:13 AM
Security Audit — agent-trust-hub — omnistudio-integration-procedure-generate