The Agent Skills Directory

[SAFE]: The skill is designed for administrative quality assurance. It provides systematic checklists for validating ServiceNow configurations and uses standard platform interaction patterns.
[COMMAND_EXECUTION]: The troubleshooting section includes an example of using a background script tool to perform syntax validation via eval(). This is restricted to checking the validity of existing scripts within the ServiceNow instance's server-side environment and is consistent with the skill's purpose.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes configuration data from ServiceNow tables (e.g., sys_script, sc_cat_item).
Ingestion points: Data is ingested via SN-Query-Table and REST API calls to ServiceNow configuration tables in SKILL.md.
Boundary markers: None present; the instructions do not include specific delimiters or warnings to ignore instructions embedded in the retrieved configuration data.
Capability inventory: The skill utilizes Bash, SN-Query-Table, SN-Validate-Configuration, and SN-Get-Table-Schema.
Sanitization: No sanitization or escaping of the configuration content is mentioned prior to the agent's analysis or reporting.

configuration-validation