The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill uses the SN-Execute-Background-Script tool to run server-side JavaScript on a ServiceNow instance for alert aggregation, noise detection, and impact analysis. These scripts are provided as templates within the skill instructions.
[COMMAND_EXECUTION]: The skill employs Bash for operational commands and makes authenticated REST API requests to ServiceNow endpoints to query alerts, update records, and configure suppression rules.
[PROMPT_INJECTION]: The skill processes untrusted data from ServiceNow alert fields, which introduces a potential surface for indirect prompt injection.
Ingestion points: Alert descriptions, sources, and other fields retrieved from the em_alert and em_event tables via MCP tools and REST APIs.
Boundary markers: The skill does not define specific delimiters or instructions to isolate external data from the agent's core instructions.
Capability inventory: The agent has access to SN-Update-Record for record modification, SN-Execute-Background-Script for server-side code execution, and Bash for command execution.
Sanitization: No explicit validation or filtering of ingested alert content is demonstrated in the procedure.

alert-analysis