itsm-kb-generation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated data from ServiceNow records, creating an attack surface for indirect prompt injection where malicious data in incidents could influence agent behavior.
- Ingestion points: Data is pulled from the
incident,problem, andsys_journal_fieldtables inSKILL.md. - Boundary markers: The skill uses structural Markdown headers to organize the generated content but does not implement explicit delimiters or 'ignore embedded instructions' markers for ingested text.
- Capability inventory: The skill has the capability to create records (
SN-Create-Record), update records (SN-Update-Record), and execute server-side JavaScript (SN-Execute-Background-Script). - Sanitization: No explicit escaping or sanitization of input data is performed before interpolation into the article template.
- [DYNAMIC_EXECUTION]: The skill utilizes
SN-Execute-Background-Scriptto run server-side JavaScript (Glide API) on the ServiceNow instance. This is a high-privilege but standard automation tool for the platform, used here for complex data aggregation. - [COMMAND_EXECUTION]: The documentation includes
bashexamples usingcurlto interact with ServiceNow's REST API, which is a standard integration practice.
Audit Metadata