The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to utilize the SN-Execute-Background-Script tool to run server-side JavaScript (GlideScript) within a ServiceNow instance to perform complex data analysis and prioritization.
[REMOTE_CODE_EXECUTION]: By utilizing background script execution, the skill enables the agent to execute arbitrary code on the target ServiceNow server, which is a high-privilege operation requiring administrative access.
[EXTERNAL_DOWNLOADS]: The skill interacts with external ServiceNow REST API endpoints (e.g., /api/now/table/sn_grc_issue) to retrieve, create, and update organizational data.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external ServiceNow records.
Ingestion points: Data is retrieved from the sn_grc_issue, sn_grc_risk, and sn_compliance_control tables (SKILL.md).
Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the retrieved data.
Capability inventory: The skill has access to high-impact capabilities including SN-Execute-Background-Script, SN-Update-Record, SN-Create-Record, and Bash execution.
Sanitization: There is no evidence of input validation or content filtering for fields like short_description or description before they are processed by the agent or included in generated scripts.

issue-action-plan