service-omni-supervisor-config-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Salesforce CLI (
sf) and standard Unix utilities (jq,grep,sed) to manage metadata deployments. These operations are restricted to the local environment and the authenticated Salesforce org. - [COMMAND_EXECUTION]: The testing framework uses
subprocess.run()to execute a bootstrap script and mock CLI environment for unit testing. This is a standard practice for local skill validation and does not pose a threat to the user environment. - [SAFE]: The skill implements a 'safe-to-write' guard, explicitly blocking execution against production Salesforce orgs unless they are Sandboxes, Trial orgs, or Developer Editions, which prevents accidental misconfiguration of live business environments.
- [SAFE]: Input validation is performed on all user-supplied arguments (such as DeveloperNames and CSV lists) using regular expressions to prevent command injection and SOQL injection vulnerabilities.
Audit Metadata