The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill provides templates for generating and executing server-side JavaScript code using the SN-Execute-Background-Script tool. This is intended to address specific ServiceNow REST API limitations when linking UI policy actions.
Evidence: Step 6 includes a code block using SN-Execute-Background-Script to execute a script that updates the catalog_variable field on the catalog_ui_policy_action table.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external database tables and provides capabilities to perform high-privilege operations, creating a surface for potential injection attacks.
Ingestion points: Multiple SN-Query-Table calls are documented in Step 3, Step 9, and the Troubleshooting sections of SKILL.md to retrieve data from question_choice, item_option_new, and catalog_ui_policy tables.
Boundary markers: Absent; there are no instructions for the agent to ignore or delimit instructions that might be embedded within the retrieved database fields.
Capability inventory: The skill utilizes SN-Create-Record, SN-Update-Record, and SN-Execute-Background-Script to perform state-changing operations on the ServiceNow instance.
Sanitization: Absent; no explicit validation or escaping logic is provided for data retrieved via queries before it is used in subsequent operations.

variable-management