The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/enable-and-report.sh executes Salesforce CLI (sf) commands to query, retrieve, and deploy metadata. These operations are standard for Salesforce administrative tasks and are performed using the agent's authorized tools.
[PRIVILEGE_ESCALATION]: The skill implements a safe_to_write guard that explicitly blocks execution if the target organization is identified as a production environment. It only allows modifications on sandboxes, developer editions, or trial organizations, which is a significant safety feature preventing unauthorized or accidental production changes.
[PROMPT_INJECTION]: The skill includes rigorous input validation for the app_developer_name argument, using a restrictive regular expression (^([A-Za-z][A-Za-z0-9]{0,14}__)?[A-Za-z][A-Za-z0-9_]{0,79}$) to ensure the input conforms to Salesforce metadata naming conventions and prevents shell injection or unexpected behavior.
[DYNAMIC_EXECUTION]: The testing utility scripts/tests/_bootstrap.py uses subprocess.run to execute the skill's main bash script. It also dynamically creates a mock sf executable in a temporary directory to simulate Salesforce API responses during testing. These patterns are localized to the test harness and represent standard, safe software testing practices.

service-omni-sidebar-configure