service-omni-work-skill-routing-configure
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runand shell scripts to interact with the Salesforce CLI (sf). This is the primary intended function of the skill for infrastructure automation. - [SAFE]: The skill implements a robust
safe_to_writeguard that queries the target Salesforce organization and blocks execution if it detects a production environment, preventing accidental configuration changes to live customer data. - [SAFE]: Input validation is applied to all parameters (
RELATED_ENTITY,FIELD,SKILL, etc.) using regular expressions to prevent command injection and ensure data follows Salesforce metadata naming conventions. - [SAFE]: XML generation for deployment uses
jqto perform character escaping (e.g., handling&,<,>), mitigating XML injection risks. - [SAFE]: The test suite uses a localized mock harness (
FakeSf) to simulate CLI interactions in a controlled, network-free environment during development testing.
Audit Metadata