The Agent Skills Directory

[COMMAND_EXECUTION]: The skill leverages the SN-Execute-Background-Script tool to perform complex server-side data analysis on the ServiceNow instance, including duplicate detection and health assessments. This matches the intended administrative scope and uses official platform capabilities.
[DATA_EXFILTRATION]: Includes code examples in SKILL.md (Example 1) for sending quality reports via email using the GlideEmailOutbound API. This is a routine operational task for generating notifications and reports within the enterprise environment.
[PROMPT_INJECTION]: Identifies an indirect prompt injection surface where the agent processes data from ServiceNow tables. 1. Ingestion points: Data retrieved from cmdb_ci and related tables in SKILL.md (Steps 1-6). 2. Boundary markers: Absent; CI attributes are processed without delimiters to separate them from instructions. 3. Capability inventory: The skill can modify data and execute scripts via SN-Update-Record, SN-Create-Record, and SN-Execute-Background-Script as documented across SKILL.md. 4. Sanitization: Absent; records are handled via standard GlideRecord API calls without specific filtering for potentially malicious prompt content embedded in fields like CI names or comments.

data-quality