The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the SN-Execute-Background-Script tool to run server-side GlideScript within a ServiceNow environment. This is a powerful administrative capability used here to perform complex cross-table joins for change correlation.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes data from external sources.
Ingestion points: Data enters the agent's context from em_alert descriptions, kb_knowledge articles, and change_request fields (referenced in SKILL.md).
Boundary markers: None identified; untrusted data from alert records is interpolated directly into queries and tool parameters.
Capability inventory: The skill has the ability to execute server-side scripts via SN-Execute-Background-Script and modify records via SN-Update-Record.
Sanitization: No explicit sanitization or validation of the ingested alert data is performed before it is used in subsequent investigation steps.

alert-investigation