sla-management

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the tool snow_execute_script_with_output, which allows for the execution of arbitrary JavaScript code within the ServiceNow instance. This is a functional requirement for ServiceNow development tasks.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves data from ServiceNow tables and offers a script execution environment.
  • Ingestion points: Data is ingested from the task_sla and contract_sla tables via snow_query_table or snow_find_artifact.
  • Boundary markers: There are no explicit markers or instructions to isolate retrieved data from command logic or script generation.
  • Capability inventory: The skill provides tools to execute scripts (snow_execute_script_with_output), create definitions (snow_sla_definition_create), and query data (snow_query_table, snow_find_artifact).
  • Sanitization: No data sanitization or escaping mechanisms are explicitly defined in the provided snippets for data returned from the ServiceNow environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:30 PM