The Agent Skills Directory

[COMMAND_EXECUTION]: The skill exposes the snow_execute_script_with_output tool, which enables the execution of arbitrary server-side JavaScript (ES5) within a ServiceNow environment.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes data from external records and possesses high-privilege capabilities. 1. Ingestion points: Data is imported from the ServiceNow incident table and other system tables via snow_query_incidents and snow_query_table. 2. Boundary markers: No explicit delimiters or 'ignore' instructions are documented for handling retrieved record content. 3. Capability inventory: The skill includes tools for executing scripts (snow_execute_script_with_output), querying tables (snow_query_table), and searching development artifacts (snow_find_artifact). 4. Sanitization: Code examples demonstrate direct property access and assignment using setValue and getValue without sanitization or validation of the ingested strings.

incident-management